Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.7508. Min Act: -0.1700
Data Index: 7005799 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.6883. Min Act: -0.1700
Data Index: 7950371 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.6258. Min Act: -0.1700
Data Index: 7591616 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.6258. Min Act: -0.1700
Data Index: 462079 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.6258. Min Act: -0.1700
Data Index: 2474688 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5633. Min Act: -0.1700
Data Index: 1070372 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5633. Min Act: -0.1700
Data Index: 7825466 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5633. Min Act: -0.1700
Data Index: 8737752 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 7105474 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 6905318 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5008. Min Act: -0.1700
Data Index: 427492 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5008. Min Act: -0.1700
Data Index: 2655425 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 863028 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5008. Min Act: -0.1700
Data Index: 307696 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5008. Min Act: -0.1700
Data Index: 4456414 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.5008. Min Act: -0.1700
Data Index: 4456153 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 1078716 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 4955249 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 5362823 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7508. Min Range: -7.7508
Max Act: 7.4383. Min Act: -0.1700
Data Index: 4243534 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19