Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0995. Min Range: -8.0995
Max Act: 8.0995. Min Act: -0.1700
Data Index: 8457390 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.9432. Min Act: -0.1700
Data Index: 7695101 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.9120. Min Act: -0.1700
Data Index: 1035403 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.8807. Min Act: -0.1700
Data Index: 3206549 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.7557. Min Act: -0.1700
Data Index: 4040005 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.6932. Min Act: -0.1700
Data Index: 4973747 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.6932. Min Act: -0.1700
Data Index: 4289487 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.6620. Min Act: -0.1700
Data Index: 3198043 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.6307. Min Act: -0.1700
Data Index: 663590 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5995. Min Act: -0.1700
Data Index: 5049692 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5682. Min Act: -0.1700
Data Index: 767809 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5682. Min Act: -0.1700
Data Index: 1637985 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5682. Min Act: -0.1700
Data Index: 7492728 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5370. Min Act: -0.1700
Data Index: 298757 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5057. Min Act: -0.1700
Data Index: 4996729 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.5057. Min Act: -0.1700
Data Index: 7253842 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.4432. Min Act: -0.1700
Data Index: 7166759 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.4432. Min Act: -0.1700
Data Index: 607601 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.4745. Min Act: -0.1700
Data Index: 8573700 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0995. Min Range: -8.0995
Max Act: 7.4432. Min Act: -0.1700
Data Index: 3574301 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19