Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.5678. Min Act: -0.1700
Data Index: 3904505 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.3178. Min Act: -0.1700
Data Index: 5391488 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.2553. Min Act: -0.1700
Data Index: 3229965 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.2553. Min Act: -0.1700
Data Index: 3904504 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.1928. Min Act: -0.1700
Data Index: 3904506 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.1928. Min Act: -0.1700
Data Index: 3904503 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.1303. Min Act: -0.1700
Data Index: 5988001 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5678. Min Range: -8.5678
Max Act: 8.0053. Min Act: -0.1700
Data Index: 114915 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.9428. Min Act: -0.1700
Data Index: 3904507 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.9116. Min Act: -0.1700
Data Index: 316463 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 685885 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.8491. Min Act: -0.1700
Data Index: 5716675 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 4786994 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 3549506 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.7866. Min Act: -0.1700
Data Index: 680605 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.7866. Min Act: -0.1700
Data Index: 5831591 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.7866. Min Act: -0.1700
Data Index: 3625105 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.7866. Min Act: -0.1700
Data Index: 1007141 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.7241. Min Act: -0.1700
Data Index: 3167354 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5678. Min Range: -8.5678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1401998 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19