Exposing the Functionalities of Neurons for Gated Recurrent Unit Based Sequence-to-Sequence Model

2023/03/27 by Yi-Ting Lee, Lee, Yi-Ting, Da-Yi Wu +5 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #Cell Image Analysis Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function

paper · pdf · doi:10.48550/arxiv.2303.15072

openalex publication_date 2023/03/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The goal of this paper is to report certain scientific discoveries about a Seq2Seq model. It is known that analyzing the behavior of RNN-based models at the neuron level is considered a more challenging task than analyzing a DNN or CNN models due to their recursive mechanism in nature. This paper aims to provide neuron-level analysis to explain why a vanilla GRU-based Seq2Seq model without attention can achieve token-positioning. We found four different types of neurons: storing, counting, triggering, and outputting and further uncover the mechanism for these neurons to work together in order to produce the right token in the right position.

Cited by

• SPH-Net: A Co-Attention Hybrid Model for Accurate Stock Price Prediction

Related

• Universal Neurons in GPT2 Language Models
• Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact
• Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
• Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
• Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks