Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.5973. Min Act: -0.1700
Data Index: 6089389 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.2848. Min Act: -0.1700
Data Index: 4459971 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.2223. Min Act: -0.1700
Data Index: 7760737 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.1598. Min Act: -0.1700
Data Index: 1204079 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.0348. Min Act: -0.1700
Data Index: 3831589 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.0973. Min Act: -0.1700
Data Index: 8450855 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.0973. Min Act: -0.1700
Data Index: 7141900 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5973. Min Range: -12.5973
Max Act: 12.0348. Min Act: -0.1700
Data Index: 6375479 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.9098. Min Act: -0.1700
Data Index: 4794917 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.9723. Min Act: -0.1700
Data Index: 5519494 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.9723. Min Act: -0.1700
Data Index: 6924758 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.9723. Min Act: -0.1700
Data Index: 3768374 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.9098. Min Act: -0.1700
Data Index: 2524531 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.9098. Min Act: -0.1700
Data Index: 6544031 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.8473. Min Act: -0.1700
Data Index: 4680673 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.8473. Min Act: -0.1700
Data Index: 3047645 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.8473. Min Act: -0.1700
Data Index: 563453 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.8473. Min Act: -0.1700
Data Index: 7359985 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.7848. Min Act: -0.1700
Data Index: 5054765 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5973. Min Range: -12.5973
Max Act: 11.7848. Min Act: -0.1700
Data Index: 919126 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19