Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.7764. Min Act: -0.1700
Data Index: 8632139 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.7246. Min Act: -0.1700
Data Index: 2047871 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.7073. Min Act: -0.1700
Data Index: 771218 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6899. Min Act: -0.1700
Data Index: 2822371 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6986. Min Act: -0.1700
Data Index: 4263774 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.7159. Min Act: -0.1700
Data Index: 4444214 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6899. Min Act: -0.1700
Data Index: 2366123 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.7073. Min Act: -0.1700
Data Index: 6268924 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6726. Min Act: -0.1700
Data Index: 5623560 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6812. Min Act: -0.1700
Data Index: 8754164 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6812. Min Act: -0.1700
Data Index: 1146662 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6726. Min Act: -0.1700
Data Index: 4024152 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6812. Min Act: -0.1700
Data Index: 21096 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6726. Min Act: -0.1700
Data Index: 6616418 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6726. Min Act: -0.1700
Data Index: 7164694 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6639. Min Act: -0.1700
Data Index: 3462474 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6465. Min Act: -0.1700
Data Index: 669687 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6726. Min Act: -0.1700
Data Index: 6358959 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6639. Min Act: -0.1689
Data Index: 5458319 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7764. Min Range: -1.7764
Max Act: 1.6726. Min Act: -0.1700
Data Index: 7580246 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19