Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4971. Min Act: -0.1700
Data Index: 5265069 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.5596. Min Act: -0.1700
Data Index: 3108786 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.5596. Min Act: -0.1700
Data Index: 8076288 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4971. Min Act: -0.1700
Data Index: 1308621 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4971. Min Act: -0.1700
Data Index: 7044344 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4971. Min Act: -0.1700
Data Index: 7411381 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4971. Min Act: -0.1700
Data Index: 3215895 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4971. Min Act: -0.1700
Data Index: 3533901 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4034. Min Act: -0.1700
Data Index: 6177621 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4034. Min Act: -0.1700
Data Index: 5843729 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3721. Min Act: -0.1700
Data Index: 7476894 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3721. Min Act: -0.1700
Data Index: 5422132 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3409. Min Act: -0.1700
Data Index: 2597411 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3096. Min Act: -0.1700
Data Index: 5721422 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3409. Min Act: -0.1700
Data Index: 5388458 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3096. Min Act: -0.1700
Data Index: 6399052 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2784. Min Act: -0.1700
Data Index: 5346500 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3096. Min Act: -0.1700
Data Index: 4244721 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2784. Min Act: -0.1700
Data Index: 1126407 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2784. Min Act: -0.1700
Data Index: 258336 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19