Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 751 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.9351. Min Act: -0.1700
Data Index: 1403205 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.9351. Min Act: -0.1700
Data Index: 8196112 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1959879 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.8726. Min Act: -0.1700
Data Index: 1522730 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.8726. Min Act: -0.1700
Data Index: 6620412 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.8413. Min Act: -0.1700
Data Index: 92502 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7788. Min Act: -0.1700
Data Index: 7340201 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7788. Min Act: -0.1700
Data Index: 1890031 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7788. Min Act: -0.1700
Data Index: 8062900 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7788. Min Act: -0.1700
Data Index: 23735 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.8101. Min Act: -0.1700
Data Index: 5409779 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7319. Min Act: -0.1700
Data Index: 7041080 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7319. Min Act: -0.1700
Data Index: 4592069 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7319. Min Act: -0.1700
Data Index: 5556592 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7319. Min Act: -0.1700
Data Index: 3732794 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7319. Min Act: -0.1700
Data Index: 8818360 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7162. Min Act: -0.1700
Data Index: 7711165 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7162. Min Act: -0.1700
Data Index: 480896 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6849. Min Act: -0.1700
Data Index: 7391873 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7006. Min Act: -0.1700
Data Index: 464043 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19