Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.3614. Min Act: -0.1700
Data Index: 422725 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.3926. Min Act: -0.1700
Data Index: 1045171 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.3614. Min Act: -0.1700
Data Index: 1025883 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2989. Min Act: -0.1700
Data Index: 3966672 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2676. Min Act: -0.1700
Data Index: 2704301 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2364. Min Act: -0.1700
Data Index: 5990635 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2364. Min Act: -0.1700
Data Index: 3083955 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2364. Min Act: -0.1700
Data Index: 5121484 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2051. Min Act: -0.1700
Data Index: 282744 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1739. Min Act: -0.1700
Data Index: 2214003 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.2051. Min Act: -0.1700
Data Index: 179458 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1739. Min Act: -0.1700
Data Index: 7751036 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1426. Min Act: -0.1700
Data Index: 3737093 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1739. Min Act: -0.1700
Data Index: 1296766 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1426. Min Act: -0.1700
Data Index: 2580849 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1114. Min Act: -0.1700
Data Index: 2625835 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1114. Min Act: -0.1700
Data Index: 1237127 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1114. Min Act: -0.1700
Data Index: 5598669 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1114. Min Act: -0.1700
Data Index: 4472190 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3926. Min Range: -7.3926
Max Act: 7.1114. Min Act: -0.1700
Data Index: 7770838 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19