Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3087. Min Range: -10.3087
Max Act: 10.3087. Min Act: -0.1700
Data Index: 6171613 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3087. Min Range: -10.3087
Max Act: 10.2462. Min Act: -0.1700
Data Index: 7629886 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3087. Min Range: -10.3087
Max Act: 10.1212. Min Act: -0.1700
Data Index: 712825 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.8087. Min Act: -0.1700
Data Index: 1724511 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.8087. Min Act: -0.1700
Data Index: 7536364 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.6212. Min Act: -0.1698
Data Index: 3178663 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.5587. Min Act: -0.1700
Data Index: 6553733 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.5587. Min Act: -0.1700
Data Index: 8534706 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.4962. Min Act: -0.1700
Data Index: 794974 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.4962. Min Act: -0.1700
Data Index: 7054736 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.4337. Min Act: -0.1700
Data Index: 4737701 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.4337. Min Act: -0.1700
Data Index: 7981770 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.4337. Min Act: -0.1700
Data Index: 2515162 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.3087. Min Act: -0.1700
Data Index: 2349920 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.3712. Min Act: -0.1700
Data Index: 6556357 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.3087. Min Act: -0.1700
Data Index: 840621 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.1837. Min Act: -0.1700
Data Index: 5054883 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.1837. Min Act: -0.1697
Data Index: 1585636 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.1837. Min Act: -0.1700
Data Index: 271810 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3087. Min Range: -10.3087
Max Act: 9.1837. Min Act: -0.1700
Data Index: 3032769 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19