Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.9346. Min Act: -0.1700
Data Index: 7158824 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.9033. Min Act: -0.1700
Data Index: 8076591 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.8408. Min Act: -0.1700
Data Index: 4171461 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.8096. Min Act: -0.1700
Data Index: 1574722 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7783. Min Act: -0.1700
Data Index: 6350880 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7783. Min Act: -0.1700
Data Index: 6578696 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7783. Min Act: -0.1700
Data Index: 8499732 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7471. Min Act: -0.1700
Data Index: 5993344 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7158. Min Act: -0.1700
Data Index: 6350881 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7158. Min Act: -0.1700
Data Index: 3765974 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7158. Min Act: -0.1700
Data Index: 7828663 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7158. Min Act: -0.1700
Data Index: 3563921 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.7158. Min Act: -0.1700
Data Index: 8287264 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6846. Min Act: -0.1700
Data Index: 964348 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6846. Min Act: -0.1700
Data Index: 2782780 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6846. Min Act: -0.1700
Data Index: 4558355 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6846. Min Act: -0.1700
Data Index: 161881 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6846. Min Act: -0.1700
Data Index: 6315519 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6846. Min Act: -0.1700
Data Index: 8533684 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9346. Min Range: -4.9346
Max Act: 4.6533. Min Act: -0.1700
Data Index: 6330003 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19