Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 517 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.9978. Min Act: -0.1700
Data Index: 1657555 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.9978. Min Act: -0.1700
Data Index: 4565121 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.9353. Min Act: -0.1700
Data Index: 4993963 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.9353. Min Act: -0.1700
Data Index: 1059365 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.8728. Min Act: -0.1700
Data Index: 2835359 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.8728. Min Act: -0.1700
Data Index: 3210296 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.7478. Min Act: -0.1700
Data Index: 3558654 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.7478. Min Act: -0.1700
Data Index: 6033909 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.6228. Min Act: -0.1700
Data Index: 3418445 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.6228. Min Act: -0.1700
Data Index: 8035171 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.6228. Min Act: -0.1700
Data Index: 7364162 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.6228. Min Act: -0.1700
Data Index: 3020275 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.5603. Min Act: -0.1700
Data Index: 5930294 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.5603. Min Act: -0.1700
Data Index: 4353584 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.6228. Min Act: -0.1700
Data Index: 8011699 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.5603. Min Act: -0.1700
Data Index: 1998464 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.5603. Min Act: -0.1700
Data Index: 6007357 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.4978. Min Act: -0.1700
Data Index: 2738104 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.4978. Min Act: -0.1700
Data Index: 3911540 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9978. Min Range: -9.9978
Max Act: 9.4978. Min Act: -0.1700
Data Index: 7354388 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19