Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.9411. Min Act: -0.1700
Data Index: 573398 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.7536. Min Act: -0.1700
Data Index: 3984453 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.7536. Min Act: -0.1700
Data Index: 7789262 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.7536. Min Act: -0.1700
Data Index: 573399 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.6286. Min Act: -0.1700
Data Index: 5266029 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.6286. Min Act: -0.1700
Data Index: 7547005 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.5973. Min Act: -0.1700
Data Index: 1221749 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.5348. Min Act: -0.1700
Data Index: 7806365 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.5036. Min Act: -0.1700
Data Index: 4189986 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.5348. Min Act: -0.1700
Data Index: 6262415 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.5036. Min Act: -0.1700
Data Index: 2963585 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.4723. Min Act: -0.1700
Data Index: 1144403 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.4723. Min Act: -0.1700
Data Index: 1163884 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.4411. Min Act: -0.1700
Data Index: 7452468 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.4723. Min Act: -0.1700
Data Index: 221135 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.4098. Min Act: -0.1700
Data Index: 5114051 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.4098. Min Act: -0.1700
Data Index: 4955082 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.3786. Min Act: -0.1700
Data Index: 5338861 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.3786. Min Act: -0.1700
Data Index: 609925 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9411. Min Range: -6.9411
Max Act: 6.3473. Min Act: -0.1700
Data Index: 6219755 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19