Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.8411. Min Act: -0.1700
Data Index: 6610615 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.6848. Min Act: -0.1700
Data Index: 4455436 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.5286. Min Act: -0.1700
Data Index: 3573870 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.4973. Min Act: -0.1700
Data Index: 7184058 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.4973. Min Act: -0.1700
Data Index: 6579336 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.5286. Min Act: -0.1700
Data Index: 3745664 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.4348. Min Act: -0.1700
Data Index: 7785735 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.4036. Min Act: -0.1700
Data Index: 6579337 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.3723. Min Act: -0.1700
Data Index: 8527991 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.3723. Min Act: -0.1700
Data Index: 8677634 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2786. Min Act: -0.1700
Data Index: 4318753 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2473. Min Act: -0.1700
Data Index: 3894962 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2786. Min Act: -0.1700
Data Index: 6282530 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2786. Min Act: -0.1700
Data Index: 4727519 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2786. Min Act: -0.1700
Data Index: 2265903 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2473. Min Act: -0.1700
Data Index: 2161798 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2161. Min Act: -0.1700
Data Index: 7847060 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.1848. Min Act: -0.1700
Data Index: 2373060 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.1536. Min Act: -0.1700
Data Index: 5199507 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8411. Min Range: -6.8411
Max Act: 6.2161. Min Act: -0.1700
Data Index: 2161795 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19