Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.5978. Min Act: -0.1700
Data Index: 2644771 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.5978. Min Act: -0.1700
Data Index: 4295764 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.4103. Min Act: -0.1700
Data Index: 6460664 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.3791. Min Act: -0.1700
Data Index: 1268461 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.3791. Min Act: -0.1700
Data Index: 7060292 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.3166. Min Act: -0.1700
Data Index: 1913331 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.2853. Min Act: -0.1700
Data Index: 4211999 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.2228. Min Act: -0.1700
Data Index: 2115422 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.1916. Min Act: -0.1700
Data Index: 1380826 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.1603. Min Act: -0.1700
Data Index: 2269109 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.1291. Min Act: -0.1700
Data Index: 701909 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.1291. Min Act: -0.1700
Data Index: 629698 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.1291. Min Act: -0.1700
Data Index: 1533944 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0978. Min Act: -0.1700
Data Index: 5174912 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0666. Min Act: -0.1700
Data Index: 6663238 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0666. Min Act: -0.1700
Data Index: 5325948 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0666. Min Act: -0.1700
Data Index: 236978 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0353. Min Act: -0.1700
Data Index: 7880385 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0353. Min Act: -0.1700
Data Index: 2313492 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5978. Min Range: -7.5978
Max Act: 7.0041. Min Act: -0.1700
Data Index: 5432278 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19