Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.8108. Min Act: -0.1700
Data Index: 79554 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.5920. Min Act: -0.1700
Data Index: 6974230 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.5295. Min Act: -0.1700
Data Index: 3520327 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.5295. Min Act: -0.1700
Data Index: 807185 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.4983. Min Act: -0.1700
Data Index: 6914467 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.4358. Min Act: -0.1700
Data Index: 6456538 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.4358. Min Act: -0.1700
Data Index: 5336005 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.4670. Min Act: -0.1700
Data Index: 4811582 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.3420. Min Act: -0.1700
Data Index: 6563788 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.3420. Min Act: -0.1700
Data Index: 1171492 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.2483. Min Act: -0.1700
Data Index: 8187815 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.2483. Min Act: -0.1700
Data Index: 6979601 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.1858. Min Act: -0.1700
Data Index: 5643560 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.1858. Min Act: -0.1700
Data Index: 61505 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.1233. Min Act: -0.1700
Data Index: 420783 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.1858. Min Act: -0.1700
Data Index: 7433630 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.1233. Min Act: -0.1700
Data Index: 1473798 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.0920. Min Act: -0.1700
Data Index: 8522382 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.1233. Min Act: -0.1700
Data Index: 1750935 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8108. Min Range: -7.8108
Max Act: 7.0608. Min Act: -0.1700
Data Index: 1545782 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19