Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1051. Min Range: -8.1051
Max Act: 8.1051. Min Act: -0.1700
Data Index: 2682681 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.6988. Min Act: -0.1700
Data Index: 4306985 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.5113. Min Act: -0.1700
Data Index: 3861688 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.3863. Min Act: -0.1700
Data Index: 2975931 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.2926. Min Act: -0.1700
Data Index: 4306986 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.0738. Min Act: -0.1700
Data Index: 8751991 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.0426. Min Act: -0.1700
Data Index: 2915383 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.0426. Min Act: -0.1700
Data Index: 6378702 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.0426. Min Act: -0.1700
Data Index: 1475820 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.0113. Min Act: -0.1700
Data Index: 6759717 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1051. Min Range: -8.1051
Max Act: 7.0113. Min Act: -0.1700
Data Index: 7193711 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.9801. Min Act: -0.1700
Data Index: 1475810 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.9488. Min Act: -0.1700
Data Index: 1475816 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.9488. Min Act: -0.1700
Data Index: 1475817 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.9488. Min Act: -0.1700
Data Index: 1475807 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.9176. Min Act: -0.1700
Data Index: 8622022 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.8863. Min Act: -0.1700
Data Index: 8166165 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 1475809 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 7873121 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1051. Min Range: -8.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 7555715 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19