Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 3790964 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.4816. Min Act: -0.1700
Data Index: 3816121 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.3879. Min Act: -0.1700
Data Index: 7808813 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.3566. Min Act: -0.1700
Data Index: 7224750 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.3566. Min Act: -0.1700
Data Index: 422289 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.2629. Min Act: -0.1700
Data Index: 2468904 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.2316. Min Act: -0.1700
Data Index: 5650608 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.2004. Min Act: -0.1700
Data Index: 7984689 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.2004. Min Act: -0.1700
Data Index: 7738629 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1379. Min Act: -0.1700
Data Index: 7712050 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1691. Min Act: -0.1700
Data Index: 8127911 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1691. Min Act: -0.1700
Data Index: 4005812 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.2004. Min Act: -0.1700
Data Index: 1862271 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1379. Min Act: -0.1700
Data Index: 1925161 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1379. Min Act: -0.1700
Data Index: 7190448 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1066. Min Act: -0.1700
Data Index: 6950933 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.0754. Min Act: -0.1700
Data Index: 7612685 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1066. Min Act: -0.1700
Data Index: 1905719 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1066. Min Act: -0.1700
Data Index: 6662438 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5441. Min Range: -7.5441
Max Act: 7.1066. Min Act: -0.1700
Data Index: 501963 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19