Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4191. Min Range: -7.4191
Max Act: 7.4191. Min Act: -0.1700
Data Index: 3066921 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.8566. Min Act: -0.1700
Data Index: 965763 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.7629. Min Act: -0.1700
Data Index: 147095 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.7004. Min Act: -0.1700
Data Index: 1111307 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.5754. Min Act: -0.1700
Data Index: 2492786 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.5754. Min Act: -0.1700
Data Index: 652204 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.5441. Min Act: -0.1700
Data Index: 8067592 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1578075 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4816. Min Act: -0.1700
Data Index: 2851403 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4504. Min Act: -0.1700
Data Index: 3602267 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4504. Min Act: -0.1700
Data Index: 501336 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 124123 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 6294901 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 8350512 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.3879. Min Act: -0.1700
Data Index: 7605599 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 6148060 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.3879. Min Act: -0.1700
Data Index: 1910446 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.3566. Min Act: -0.1700
Data Index: 232972 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.3566. Min Act: -0.1700
Data Index: 1442624 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4191. Min Range: -7.4191
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4165496 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19