Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 699 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.3047. Min Act: -0.1700
Data Index: 6963888 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2890. Min Act: -0.1700
Data Index: 8224777 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2733. Min Act: -0.1700
Data Index: 7408810 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2105. Min Act: -0.1700
Data Index: 6180425 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1948. Min Act: -0.1700
Data Index: 8736411 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1948. Min Act: -0.1700
Data Index: 2308337 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1790. Min Act: -0.1700
Data Index: 3262441 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1790. Min Act: -0.1700
Data Index: 6262447 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1633. Min Act: -0.1700
Data Index: 2855024 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1633. Min Act: -0.1700
Data Index: 1903653 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1476. Min Act: -0.1700
Data Index: 4850015 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1318. Min Act: -0.1700
Data Index: 538526 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1476. Min Act: -0.1700
Data Index: 4879587 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1476. Min Act: -0.1700
Data Index: 8148114 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1318. Min Act: -0.1700
Data Index: 4997450 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1318. Min Act: -0.1700
Data Index: 7312725 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1161. Min Act: -0.1700
Data Index: 2993062 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1318. Min Act: -0.1700
Data Index: 3033051 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1476. Min Act: -0.1700
Data Index: 5307344 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1318. Min Act: -0.1700
Data Index: 5184485 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19