Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.7986. Min Act: -0.1700
Data Index: 6140978 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.7673. Min Act: -0.1700
Data Index: 4640491 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.6423. Min Act: -0.1700
Data Index: 6660497 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.6111. Min Act: -0.1700
Data Index: 6375737 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.6111. Min Act: -0.1700
Data Index: 4470524 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.5486. Min Act: -0.1700
Data Index: 6406328 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.5486. Min Act: -0.1700
Data Index: 960460 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.5486. Min Act: -0.1700
Data Index: 2704263 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.5486. Min Act: -0.1700
Data Index: 4683564 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.5486. Min Act: -0.1700
Data Index: 4632023 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4861. Min Act: -0.1700
Data Index: 7975492 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4861. Min Act: -0.1700
Data Index: 5007562 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4861. Min Act: -0.1700
Data Index: 7997773 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4861. Min Act: -0.1700
Data Index: 2584195 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4861. Min Act: -0.1700
Data Index: 7153699 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4548. Min Act: -0.1700
Data Index: 2949215 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4548. Min Act: -0.1700
Data Index: 1517192 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4548. Min Act: -0.1700
Data Index: 5282488 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4548. Min Act: -0.1700
Data Index: 6255584 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7986. Min Range: -6.7986
Max Act: 6.4548. Min Act: -0.1700
Data Index: 3264801 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19