Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.8309. Min Act: -0.1700
Data Index: 8178839 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.5496. Min Act: -0.1700
Data Index: 1138847 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.5496. Min Act: -0.1700
Data Index: 2021530 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.3309. Min Act: -0.1700
Data Index: 1878294 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.3309. Min Act: -0.1700
Data Index: 2924762 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.4246. Min Act: -0.1700
Data Index: 3466183 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.3621. Min Act: -0.1700
Data Index: 2099535 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.2371. Min Act: -0.1700
Data Index: 362576 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.3621. Min Act: -0.1700
Data Index: 4994944 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.1746. Min Act: -0.1700
Data Index: 8118444 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.2684. Min Act: -0.1700
Data Index: 4994943 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.2684. Min Act: -0.1700
Data Index: 1884452 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.1121. Min Act: -0.1700
Data Index: 5394376 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.0809. Min Act: -0.1700
Data Index: 5520632 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.0496. Min Act: -0.1700
Data Index: 5619407 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.1434. Min Act: -0.1700
Data Index: 3497821 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.0184. Min Act: -0.1700
Data Index: 855570 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.0496. Min Act: -0.1700
Data Index: 2533968 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.0184. Min Act: -0.1700
Data Index: 7230094 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8309. Min Range: -6.8309
Max Act: 6.1434. Min Act: -0.1700
Data Index: 1785569 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19