Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1293 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.8335. Min Act: -0.1700
Data Index: 3685247 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.8023. Min Act: -0.1700
Data Index: 791689 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.7398. Min Act: -0.1700
Data Index: 7632654 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.7398. Min Act: -0.1700
Data Index: 3234941 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.6460. Min Act: -0.1700
Data Index: 6592300 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.6148. Min Act: -0.1700
Data Index: 6628961 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.5835. Min Act: -0.1700
Data Index: 6989732 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.6148. Min Act: -0.1700
Data Index: 5442309 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.5835. Min Act: -0.1700
Data Index: 7350134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.5523. Min Act: -0.1700
Data Index: 2014373 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.5523. Min Act: -0.1700
Data Index: 644266 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.4898. Min Act: -0.1700
Data Index: 1917205 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.4898. Min Act: -0.1700
Data Index: 2510355 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.4585. Min Act: -0.1700
Data Index: 1471116 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.4585. Min Act: -0.1700
Data Index: 2943350 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.3960. Min Act: -0.1700
Data Index: 793073 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.4273. Min Act: -0.1700
Data Index: 2310975 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.3960. Min Act: -0.1700
Data Index: 3910053 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.3960. Min Act: -0.1700
Data Index: 5752866 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8335. Min Range: -6.8335
Max Act: 6.3960. Min Act: -0.1700
Data Index: 6053612 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19