Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1774 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.3969. Min Act: -0.1700
Data Index: 6544245 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.3344. Min Act: -0.1700
Data Index: 3345109 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.1156. Min Act: -0.1700
Data Index: 3883234 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.1156. Min Act: -0.1700
Data Index: 4146581 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.0531. Min Act: -0.1700
Data Index: 2996109 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.0531. Min Act: -0.1700
Data Index: 1349510 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3969. Min Range: -6.3969
Max Act: 6.0219. Min Act: -0.1700
Data Index: 6104393 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.9906. Min Act: -0.1700
Data Index: 7837786 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.9906. Min Act: -0.1700
Data Index: 7509463 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.9594. Min Act: -0.1700
Data Index: 6968761 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8656. Min Act: -0.1700
Data Index: 4107760 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8344. Min Act: -0.1700
Data Index: 5200589 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8656. Min Act: -0.1700
Data Index: 3182695 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8344. Min Act: -0.1700
Data Index: 7627367 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8344. Min Act: -0.1700
Data Index: 3096271 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8344. Min Act: -0.1700
Data Index: 3655140 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8344. Min Act: -0.1700
Data Index: 875144 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8031. Min Act: -0.1700
Data Index: 1762576 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8031. Min Act: -0.1700
Data Index: 2986406 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3969. Min Range: -6.3969
Max Act: 5.8031. Min Act: -0.1700
Data Index: 1870727 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19