Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.8010. Min Act: -0.1700
Data Index: 1199469 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.7385. Min Act: -0.1700
Data Index: 4054454 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.7385. Min Act: -0.1700
Data Index: 4054457 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.6760. Min Act: -0.1700
Data Index: 1265617 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.5823. Min Act: -0.1700
Data Index: 5939674 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.6135. Min Act: -0.1700
Data Index: 7964458 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.5510. Min Act: -0.1700
Data Index: 2806402 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.5510. Min Act: -0.1700
Data Index: 872724 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4885. Min Act: -0.1700
Data Index: 5939671 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4573. Min Act: -0.1700
Data Index: 6072571 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4573. Min Act: -0.1700
Data Index: 1158223 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4260. Min Act: -0.1700
Data Index: 406989 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4573. Min Act: -0.1700
Data Index: 207822 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.3948. Min Act: -0.1700
Data Index: 1020219 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4260. Min Act: -0.1700
Data Index: 6229883 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.4260. Min Act: -0.1700
Data Index: 6457095 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.3948. Min Act: -0.1700
Data Index: 5944490 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.3323. Min Act: -0.1700
Data Index: 8403267 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.3635. Min Act: -0.1700
Data Index: 6598917 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8010. Min Range: -6.8010
Max Act: 6.3323. Min Act: -0.1700
Data Index: 1640833 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19