Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6098 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.7284. Min Act: -0.1700
Data Index: 6468738 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.4784. Min Act: -0.1700
Data Index: 5527184 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.4784. Min Act: -0.1700
Data Index: 2021623 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.3534. Min Act: -0.1700
Data Index: 5513859 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.3534. Min Act: -0.1700
Data Index: 42956 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.2909. Min Act: -0.1700
Data Index: 827693 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.2284. Min Act: -0.1700
Data Index: 4271920 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1659. Min Act: -0.1700
Data Index: 4339687 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1034. Min Act: -0.1700
Data Index: 4879698 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1034. Min Act: -0.1700
Data Index: 3871713 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1034. Min Act: -0.1700
Data Index: 953815 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1034. Min Act: -0.1700
Data Index: 2095904 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1034. Min Act: -0.1700
Data Index: 1707180 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1659. Min Act: -0.1700
Data Index: 7002127 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.1034. Min Act: -0.1700
Data Index: 1477404 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.0409. Min Act: -0.1700
Data Index: 325328 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.0409. Min Act: -0.1700
Data Index: 7074042 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.0409. Min Act: -0.1700
Data Index: 4291114 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7284. Min Range: -8.7284
Max Act: 8.0409. Min Act: -0.1700
Data Index: 2924123 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7284. Min Range: -8.7284
Max Act: 7.9784. Min Act: -0.1700
Data Index: 1478529 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19