Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 629 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.4479. Min Act: -0.1700
Data Index: 2987031 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.4479. Min Act: -0.1700
Data Index: 8779776 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.3854. Min Act: -0.1700
Data Index: 7105257 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.2604. Min Act: -0.1700
Data Index: 7650430 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.2604. Min Act: -0.1700
Data Index: 6608780 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.2604. Min Act: -0.1700
Data Index: 5526679 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4479. Min Range: -8.4479
Max Act: 8.1979. Min Act: -0.1700
Data Index: 8008803 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 7564239 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.9791. Min Act: -0.1700
Data Index: 569015 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 6283873 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.9166. Min Act: -0.1700
Data Index: 1855558 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.7291. Min Act: -0.1700
Data Index: 6221273 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 5482945 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.7916. Min Act: -0.1700
Data Index: 7735434 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.6979. Min Act: -0.1700
Data Index: 3461072 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.6666. Min Act: -0.1700
Data Index: 1440420 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.6041. Min Act: -0.1700
Data Index: 6103110 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.6666. Min Act: -0.1700
Data Index: 5382836 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.5416. Min Act: -0.1700
Data Index: 709426 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4479. Min Range: -8.4479
Max Act: 7.5104. Min Act: -0.1700
Data Index: 543233 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19