Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.3974. Min Act: -0.1700
Data Index: 8801594 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.3349. Min Act: -0.1700
Data Index: 329372 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.3662. Min Act: -0.1700
Data Index: 4116475 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.3349. Min Act: -0.1700
Data Index: 7914525 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.2412. Min Act: -0.1700
Data Index: 5609975 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.2099. Min Act: -0.1700
Data Index: 7495 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.1787. Min Act: -0.1700
Data Index: 6809557 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.2099. Min Act: -0.1700
Data Index: 461444 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.1787. Min Act: -0.1700
Data Index: 7720483 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.1162. Min Act: -0.1700
Data Index: 6989662 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.1162. Min Act: -0.1700
Data Index: 3779800 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 7552166 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 1564815 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 7832211 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 5902400 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 715914 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 1580829 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 8425332 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0537. Min Act: -0.1700
Data Index: 5358533 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3974. Min Range: -7.3974
Max Act: 7.0224. Min Act: -0.1700
Data Index: 6479405 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19