Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3986. Min Range: -6.3986
Max Act: 6.3986. Min Act: -0.1700
Data Index: 1322768 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3986. Min Range: -6.3986
Max Act: 6.1799. Min Act: -0.1700
Data Index: 4119979 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3986. Min Range: -6.3986
Max Act: 6.1486. Min Act: -0.1700
Data Index: 7999635 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3986. Min Range: -6.3986
Max Act: 6.0236. Min Act: -0.1700
Data Index: 3087245 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3986. Min Range: -6.3986
Max Act: 6.0236. Min Act: -0.1700
Data Index: 220551 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.9299. Min Act: -0.1700
Data Index: 311162 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.9611. Min Act: -0.1700
Data Index: 6898705 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.9299. Min Act: -0.1700
Data Index: 7984913 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.9299. Min Act: -0.1700
Data Index: 3973797 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.8674. Min Act: -0.1700
Data Index: 3314851 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.8361. Min Act: -0.1700
Data Index: 4913720 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.7424. Min Act: -0.1700
Data Index: 2383473 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.8049. Min Act: -0.1700
Data Index: 8058258 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.7424. Min Act: -0.1700
Data Index: 1646089 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.6799. Min Act: -0.1700
Data Index: 8689826 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.6799. Min Act: -0.1700
Data Index: 6179292 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.6486. Min Act: -0.1700
Data Index: 5462889 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.6174. Min Act: -0.1700
Data Index: 3118696 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.6174. Min Act: -0.1700
Data Index: 2671550 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3986. Min Range: -6.3986
Max Act: 5.6174. Min Act: -0.1700
Data Index: 2913123 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19