Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 917 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8541. Min Range: -7.8541
Max Act: 7.8541. Min Act: -0.1700
Data Index: 5570497 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8541. Min Range: -7.8541
Max Act: 7.0103. Min Act: -0.1700
Data Index: 1132660 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.9791. Min Act: -0.1658
Data Index: 1398698 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.9166. Min Act: -0.1700
Data Index: 8736000 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.9478. Min Act: -0.1700
Data Index: 8811418 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.8228. Min Act: -0.1700
Data Index: 1370947 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.7603. Min Act: -0.1700
Data Index: 7145462 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.7291. Min Act: -0.1700
Data Index: 1661905 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.7603. Min Act: -0.1700
Data Index: 4699666 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6978. Min Act: -0.1700
Data Index: 5369449 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6978. Min Act: -0.1700
Data Index: 5935452 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6666. Min Act: -0.1700
Data Index: 8611470 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6353. Min Act: -0.1700
Data Index: 2850508 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6353. Min Act: -0.1700
Data Index: 8442194 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6353. Min Act: -0.1700
Data Index: 6861686 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6353. Min Act: -0.1699
Data Index: 8611477 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6041. Min Act: -0.1700
Data Index: 3145007 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6353. Min Act: -0.1700
Data Index: 8633840 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.6353. Min Act: -0.1700
Data Index: 3791316 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8541. Min Range: -7.8541
Max Act: 6.5728. Min Act: -0.1700
Data Index: 1103940 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19