Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.6315. Min Act: -0.1700
Data Index: 4184464 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4750. Min Act: -0.1700
Data Index: 7722740 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4750. Min Act: -0.1700
Data Index: 1246605 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4593. Min Act: -0.1700
Data Index: 7762605 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4750. Min Act: -0.1700
Data Index: 7961715 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4436. Min Act: -0.1700
Data Index: 1954587 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4123. Min Act: -0.1700
Data Index: 3363592 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4279. Min Act: -0.1700
Data Index: 6737993 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4279. Min Act: -0.1700
Data Index: 4226387 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4436. Min Act: -0.1700
Data Index: 6954814 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4279. Min Act: -0.1700
Data Index: 8485898 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3966. Min Act: -0.1700
Data Index: 138134 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.4123. Min Act: -0.1700
Data Index: 632030 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3966. Min Act: -0.1700
Data Index: 3675067 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3809. Min Act: -0.1700
Data Index: 166386 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3809. Min Act: -0.1700
Data Index: 3671304 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3809. Min Act: -0.1700
Data Index: 7876329 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3809. Min Act: -0.1700
Data Index: 2814720 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3652. Min Act: -0.1700
Data Index: 2939541 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6315. Min Range: -3.6315
Max Act: 3.3652. Min Act: -0.1700
Data Index: 477880 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19