Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.5475. Min Act: -0.1700
Data Index: 8692048 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.4850. Min Act: -0.1700
Data Index: 934580 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.4538. Min Act: -0.1700
Data Index: 737705 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.3913. Min Act: -0.1700
Data Index: 3337320 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.3600. Min Act: -0.1700
Data Index: 4904497 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.3288. Min Act: -0.1700
Data Index: 7024059 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2975. Min Act: -0.1700
Data Index: 1014274 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2975. Min Act: -0.1700
Data Index: 1683344 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2663. Min Act: -0.1700
Data Index: 1216262 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2663. Min Act: -0.1700
Data Index: 5011599 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2350. Min Act: -0.1700
Data Index: 1334153 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2350. Min Act: -0.1700
Data Index: 8486068 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2350. Min Act: -0.1700
Data Index: 186101 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2350. Min Act: -0.1700
Data Index: 7021722 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2038. Min Act: -0.1700
Data Index: 1940448 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.1725. Min Act: -0.1700
Data Index: 3591049 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2038. Min Act: -0.1700
Data Index: 535227 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2038. Min Act: -0.1700
Data Index: 5705272 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2038. Min Act: -0.1700
Data Index: 649731 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5475. Min Range: -7.5475
Max Act: 7.2350. Min Act: -0.1700
Data Index: 6470296 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19