Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.8247. Min Act: -0.1700
Data Index: 3557431 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.7934. Min Act: -0.1700
Data Index: 5558764 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.7622. Min Act: -0.1700
Data Index: 8191350 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.7309. Min Act: -0.1700
Data Index: 8524251 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.7309. Min Act: -0.1700
Data Index: 8357101 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6684. Min Act: -0.1700
Data Index: 5170224 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6684. Min Act: -0.1700
Data Index: 1479589 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6684. Min Act: -0.1700
Data Index: 1139050 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6372. Min Act: -0.1700
Data Index: 5740251 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6372. Min Act: -0.1700
Data Index: 8117624 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6372. Min Act: -0.1700
Data Index: 156654 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6372. Min Act: -0.1700
Data Index: 8191351 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6059. Min Act: -0.1700
Data Index: 8068432 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5540066 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.5747. Min Act: -0.1700
Data Index: 343186 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.5747. Min Act: -0.1700
Data Index: 6825184 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.5747. Min Act: -0.1700
Data Index: 6756113 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.5747. Min Act: -0.1700
Data Index: 4608536 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.5122. Min Act: -0.1700
Data Index: 5415775 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8247. Min Range: -5.8247
Max Act: 5.4809. Min Act: -0.1700
Data Index: 4348652 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19