Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 466 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2982. Min Range: -7.2982
Max Act: 7.2982. Min Act: -0.1700
Data Index: 715401 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2982. Min Range: -7.2982
Max Act: 7.1732. Min Act: -0.1700
Data Index: 3461103 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2982. Min Range: -7.2982
Max Act: 7.0482. Min Act: -0.1700
Data Index: 3804314 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2982. Min Range: -7.2982
Max Act: 7.0169. Min Act: -0.1700
Data Index: 2898169 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.9857. Min Act: -0.1700
Data Index: 6786581 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.9857. Min Act: -0.1700
Data Index: 5369464 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.9232. Min Act: -0.1700
Data Index: 4957493 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8919. Min Act: -0.1700
Data Index: 7216373 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8919. Min Act: -0.1700
Data Index: 2136393 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8919. Min Act: -0.1700
Data Index: 5073302 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.9232. Min Act: -0.1700
Data Index: 472938 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8607. Min Act: -0.1700
Data Index: 5744024 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8919. Min Act: -0.1700
Data Index: 2446180 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8607. Min Act: -0.1700
Data Index: 3279404 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8607. Min Act: -0.1700
Data Index: 3966511 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8294. Min Act: -0.1700
Data Index: 4570117 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8294. Min Act: -0.1700
Data Index: 5089351 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.8294. Min Act: -0.1700
Data Index: 1725614 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.7982. Min Act: -0.1700
Data Index: 3527511 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2982. Min Range: -7.2982
Max Act: 6.7982. Min Act: -0.1700
Data Index: 5263655 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19