Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.7505. Min Act: -0.1700
Data Index: 3483124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.7193. Min Act: -0.1700
Data Index: 5651048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.7193. Min Act: -0.1700
Data Index: 503856 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.7193. Min Act: -0.1700
Data Index: 7837682 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.6880. Min Act: -0.1700
Data Index: 341706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.6880. Min Act: -0.1700
Data Index: 6031391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.6567. Min Act: -0.1700
Data Index: 663504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 3475919 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.6254. Min Act: -0.1700
Data Index: 4464706 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 8287829 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 7721076 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 2942468 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 7030577 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 6408668 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 5693543 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5941. Min Act: -0.1700
Data Index: 5507852 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5628. Min Act: -0.1700
Data Index: 53292 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5628. Min Act: -0.1700
Data Index: 3750460 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5628. Min Act: -0.1700
Data Index: 507265 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7505. Min Range: -3.7505
Max Act: 3.5628. Min Act: -0.1700
Data Index: 686239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19