Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5348. Min Range: -11.5348
Max Act: 11.5348. Min Act: -0.1700
Data Index: 5997764 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5348. Min Range: -11.5348
Max Act: 11.0973. Min Act: -0.1700
Data Index: 2649147 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5348. Min Range: -11.5348
Max Act: 11.0348. Min Act: -0.1700
Data Index: 3087045 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5348. Min Range: -11.5348
Max Act: 11.0973. Min Act: -0.1700
Data Index: 4041249 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5348. Min Range: -11.5348
Max Act: 11.0348. Min Act: -0.1700
Data Index: 5639811 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.9723. Min Act: -0.1700
Data Index: 6089270 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7848. Min Act: -0.1700
Data Index: 7075329 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7848. Min Act: -0.1700
Data Index: 3946128 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7848. Min Act: -0.1700
Data Index: 6572752 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7848. Min Act: -0.1700
Data Index: 3130470 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.8473. Min Act: -0.1700
Data Index: 6744128 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7223. Min Act: -0.1700
Data Index: 3038423 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7223. Min Act: -0.1700
Data Index: 4932695 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7223. Min Act: -0.1700
Data Index: 2752587 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7223. Min Act: -0.1700
Data Index: 3261925 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.7223. Min Act: -0.1700
Data Index: 3985 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.6598. Min Act: -0.1700
Data Index: 5377938 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.6598. Min Act: -0.1700
Data Index: 1484824 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.5973. Min Act: -0.1700
Data Index: 4383204 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5348. Min Range: -11.5348
Max Act: 10.5973. Min Act: -0.1700
Data Index: 729473 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19