Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.8439. Min Act: -0.1700
Data Index: 3846865 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.8281. Min Act: -0.1700
Data Index: 3354602 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.8121. Min Act: -0.1700
Data Index: 4467660 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7962. Min Act: -0.1700
Data Index: 4354642 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7643. Min Act: -0.1700
Data Index: 7923059 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7803. Min Act: -0.1700
Data Index: 586619 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 1947272 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7643. Min Act: -0.1700
Data Index: 179601 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7643. Min Act: -0.1700
Data Index: 344815 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 5683167 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7643. Min Act: -0.1700
Data Index: 2308108 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 7562149 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 5347509 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 2462145 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 6174382 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 7694273 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7324. Min Act: -0.1700
Data Index: 1222477 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7324. Min Act: -0.1700
Data Index: 6367636 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7004. Min Act: -0.1700
Data Index: 4360542 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8439. Min Range: -2.8439
Max Act: 2.7484. Min Act: -0.1700
Data Index: 8034579 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19