Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0314. Min Range: -7.0314
Max Act: 7.0314. Min Act: -0.1700
Data Index: 5375053 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0314. Min Range: -7.0314
Max Act: 7.0314. Min Act: -0.1700
Data Index: 8565229 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0314. Min Range: -7.0314
Max Act: 7.0001. Min Act: -0.1700
Data Index: 5175633 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.9689. Min Act: -0.1700
Data Index: 3710513 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.9689. Min Act: -0.1700
Data Index: 8831392 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0314. Min Range: -7.0314
Max Act: 7.0001. Min Act: -0.1700
Data Index: 7708000 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.9376. Min Act: -0.1700
Data Index: 8098350 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8439. Min Act: -0.1700
Data Index: 8492447 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8439. Min Act: -0.1700
Data Index: 563894 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8439. Min Act: -0.1700
Data Index: 5067897 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8439. Min Act: -0.1700
Data Index: 2820554 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8439. Min Act: -0.1699
Data Index: 3293746 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8126. Min Act: -0.1700
Data Index: 7952672 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.8126. Min Act: -0.1700
Data Index: 89504 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.7501. Min Act: -0.1700
Data Index: 3860389 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.7501. Min Act: -0.1700
Data Index: 2727394 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.7501. Min Act: -0.1700
Data Index: 3794779 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.7501. Min Act: -0.1700
Data Index: 7093112 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.7501. Min Act: -0.1700
Data Index: 8290577 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0314. Min Range: -7.0314
Max Act: 6.7501. Min Act: -0.1700
Data Index: 2592312 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19