Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1313. Min Range: -1.1313
Max Act: 1.1313. Min Act: -0.1700
Data Index: 4574485 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.9744. Min Act: -0.1700
Data Index: 3119759 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.9744. Min Act: -0.1700
Data Index: 1437984 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.8459. Min Act: -0.1700
Data Index: 4019260 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.8459. Min Act: -0.1700
Data Index: 6683514 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.8290. Min Act: -0.1700
Data Index: 4941155 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.8121. Min Act: -0.1700
Data Index: 1938642 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7953. Min Act: -0.1700
Data Index: 382547 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.8121. Min Act: -0.1700
Data Index: 5551409 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.8037. Min Act: -0.1700
Data Index: 2468581 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7703. Min Act: -0.1700
Data Index: 7998798 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7537. Min Act: -0.1700
Data Index: 4357354 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7620. Min Act: -0.1700
Data Index: 4564901 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7620. Min Act: -0.1700
Data Index: 6888106 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7454. Min Act: -0.1700
Data Index: 6252827 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7537. Min Act: -0.1700
Data Index: 1498914 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7620. Min Act: -0.1700
Data Index: 5073710 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7454. Min Act: -0.1700
Data Index: 5807695 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7454. Min Act: -0.1700
Data Index: 5682323 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1313. Min Range: -1.1313
Max Act: 0.7371. Min Act: -0.1700
Data Index: 2645820 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19