Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.7198. Min Act: -0.1700
Data Index: 1641089 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6261. Min Act: -0.1700
Data Index: 1108776 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5948. Min Act: -0.1700
Data Index: 1930984 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6261. Min Act: -0.1700
Data Index: 4864840 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6261. Min Act: -0.1700
Data Index: 484379 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6573. Min Act: -0.1700
Data Index: 5646769 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6969297 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5636. Min Act: -0.1700
Data Index: 4415709 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5636. Min Act: -0.1700
Data Index: 7671505 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5323. Min Act: -0.1700
Data Index: 8722685 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4361419 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5323. Min Act: -0.1700
Data Index: 627403 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5323. Min Act: -0.1700
Data Index: 7787261 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 7648283 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 5587880 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 4957749 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 7230046 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 7033661 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 2939821 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 1108570 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19