Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6020 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.6892. Min Act: -0.1700
Data Index: 3141084 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.4079. Min Act: -0.1700
Data Index: 7575318 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.3454. Min Act: -0.1700
Data Index: 3115214 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.3142. Min Act: -0.1700
Data Index: 2172155 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.2204. Min Act: -0.1700
Data Index: 670607 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.2204. Min Act: -0.1700
Data Index: 4661547 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 8037276 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 108241 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 3588324 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 6414595 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 1775831 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 1497761 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0017. Min Act: -0.1700
Data Index: 4672974 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0329. Min Act: -0.1700
Data Index: 1560669 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0642. Min Act: -0.1700
Data Index: 7760607 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0017. Min Act: -0.1700
Data Index: 4879207 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6892. Min Range: -6.6892
Max Act: 6.0017. Min Act: -0.1700
Data Index: 472834 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6892. Min Range: -6.6892
Max Act: 5.9704. Min Act: -0.1700
Data Index: 989425 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6892. Min Range: -6.6892
Max Act: 5.9704. Min Act: -0.1700
Data Index: 5549253 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6892. Min Range: -6.6892
Max Act: 5.9392. Min Act: -0.1700
Data Index: 5827236 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19