Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.9502. Min Act: -0.1700
Data Index: 8363452 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.8565. Min Act: -0.1700
Data Index: 2981263 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.7315. Min Act: -0.1700
Data Index: 1566296 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.7002. Min Act: -0.1700
Data Index: 8260803 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.4502. Min Act: -0.1700
Data Index: 4498571 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.3877. Min Act: -0.1700
Data Index: 923102 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.3877. Min Act: -0.1700
Data Index: 468982 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.3565. Min Act: -0.1700
Data Index: 2880039 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.3877. Min Act: -0.1700
Data Index: 3105039 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.3565. Min Act: -0.1700
Data Index: 6292506 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.3252. Min Act: -0.1700
Data Index: 7778522 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2940. Min Act: -0.1700
Data Index: 7774424 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2627. Min Act: -0.1700
Data Index: 3467 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2315. Min Act: -0.1700
Data Index: 5271713 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2315. Min Act: -0.1700
Data Index: 1996814 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2002. Min Act: -0.1700
Data Index: 7361454 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2467330 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2694064 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2315. Min Act: -0.1700
Data Index: 4877644 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9502. Min Range: -7.9502
Max Act: 7.2002. Min Act: -0.1700
Data Index: 6288628 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19