Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.6602. Min Act: -0.1700
Data Index: 8198594 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.4727. Min Act: -0.1700
Data Index: 6808141 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.4102. Min Act: -0.1700
Data Index: 4027952 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.3790. Min Act: -0.1700
Data Index: 2774916 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.3790. Min Act: -0.1700
Data Index: 1570002 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.3477. Min Act: -0.1700
Data Index: 4827000 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.2852. Min Act: -0.1700
Data Index: 3527430 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.1915. Min Act: -0.1700
Data Index: 1803419 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.1602. Min Act: -0.1700
Data Index: 4469386 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.1602. Min Act: -0.1700
Data Index: 2518775 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0977. Min Act: -0.1700
Data Index: 2950141 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0977. Min Act: -0.1700
Data Index: 8360848 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0665. Min Act: -0.1700
Data Index: 139201 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0665. Min Act: -0.1700
Data Index: 6217415 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0977. Min Act: -0.1700
Data Index: 7782920 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 6150097 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 7100529 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 7012589 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 3991269 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6602. Min Range: -5.6602
Max Act: 5.0040. Min Act: -0.1700
Data Index: 7401391 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19