Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.7557. Min Act: -0.1700
Data Index: 5614185 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.3494. Min Act: -0.1700
Data Index: 5597190 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.3182. Min Act: -0.1700
Data Index: 2440795 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.2869. Min Act: -0.1700
Data Index: 5046308 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.2244. Min Act: -0.1700
Data Index: 4166308 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.2244. Min Act: -0.1700
Data Index: 8731391 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.1932. Min Act: -0.1700
Data Index: 298490 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.1619. Min Act: -0.1700
Data Index: 2573382 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4573202 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.1307. Min Act: -0.1700
Data Index: 3870597 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 8555045 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0994. Min Act: -0.1700
Data Index: 8025298 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 3270267 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 284146 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 8354823 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 3610977 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 3448347 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0369. Min Act: -0.1700
Data Index: 7173295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0057. Min Act: -0.1700
Data Index: 7722222 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7557. Min Range: -6.7557
Max Act: 6.0057. Min Act: -0.1700
Data Index: 7701963 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19