Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2597 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1451. Min Range: -8.1451
Max Act: 8.1451. Min Act: -0.1700
Data Index: 8685580 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1451. Min Range: -8.1451
Max Act: 8.0826. Min Act: -0.1700
Data Index: 6346807 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1451. Min Range: -8.1451
Max Act: 8.0826. Min Act: -0.1700
Data Index: 2198785 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1451. Min Range: -8.1451
Max Act: 8.0201. Min Act: -0.1700
Data Index: 4855695 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1451. Min Range: -8.1451
Max Act: 8.0201. Min Act: -0.1700
Data Index: 7990151 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.9576. Min Act: -0.1700
Data Index: 3394909 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.9576. Min Act: -0.1700
Data Index: 1674786 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1451. Min Range: -8.1451
Max Act: 8.0201. Min Act: -0.1700
Data Index: 149790 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8951. Min Act: -0.1700
Data Index: 7325372 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8326. Min Act: -0.1700
Data Index: 5552199 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8951. Min Act: -0.1700
Data Index: 8685579 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8326. Min Act: -0.1700
Data Index: 2198787 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8951. Min Act: -0.1700
Data Index: 3273748 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8326. Min Act: -0.1700
Data Index: 7329314 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8326. Min Act: -0.1700
Data Index: 7579321 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8013. Min Act: -0.1700
Data Index: 4973826 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.7701. Min Act: -0.1700
Data Index: 2855559 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8013. Min Act: -0.1700
Data Index: 932848 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.7701. Min Act: -0.1700
Data Index: 6810801 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1451. Min Range: -8.1451
Max Act: 7.8013. Min Act: -0.1700
Data Index: 7914960 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19