Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1855 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.9692. Min Act: -0.1700
Data Index: 4668125 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.9066. Min Act: -0.1700
Data Index: 1418398 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.9066. Min Act: -0.1700
Data Index: 2160964 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.8441. Min Act: -0.1700
Data Index: 426385 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.8128. Min Act: -0.1700
Data Index: 1734524 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.8128. Min Act: -0.1700
Data Index: 1205863 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7972. Min Act: -0.1700
Data Index: 7269104 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7972. Min Act: -0.1700
Data Index: 2770784 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7659. Min Act: -0.1700
Data Index: 7557903 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7659. Min Act: -0.1700
Data Index: 7854265 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7659. Min Act: -0.1700
Data Index: 7687178 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7659. Min Act: -0.1700
Data Index: 4942291 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7503. Min Act: -0.1700
Data Index: 6791406 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7503. Min Act: -0.1700
Data Index: 7989409 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7503. Min Act: -0.1700
Data Index: 5896435 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7503. Min Act: -0.1700
Data Index: 1854538 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7346. Min Act: -0.1700
Data Index: 1205810 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7346. Min Act: -0.1700
Data Index: 4545345 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7346. Min Act: -0.1700
Data Index: 1826352 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9692. Min Range: -3.9692
Max Act: 3.7346. Min Act: -0.1700
Data Index: 5329258 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19