Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.9321. Min Act: -0.1700
Data Index: 6614957 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.9321. Min Act: -0.1700
Data Index: 8468204 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.8696. Min Act: -0.1700
Data Index: 1925872 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.8383. Min Act: -0.1700
Data Index: 5922616 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7758. Min Act: -0.1700
Data Index: 3523239 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7446. Min Act: -0.1700
Data Index: 2290757 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.8071. Min Act: -0.1700
Data Index: 1579211 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7133. Min Act: -0.1700
Data Index: 364436 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7446. Min Act: -0.1700
Data Index: 990294 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7446. Min Act: -0.1700
Data Index: 3134704 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.6821. Min Act: -0.1700
Data Index: 2851810 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7133. Min Act: -0.1700
Data Index: 631787 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.7133. Min Act: -0.1700
Data Index: 3893780 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.6508. Min Act: -0.1700
Data Index: 5733522 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.6508. Min Act: -0.1700
Data Index: 6842966 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.6196. Min Act: -0.1700
Data Index: 5608345 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.6196. Min Act: -0.1700
Data Index: 2249799 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.5883. Min Act: -0.1700
Data Index: 7627111 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.5883. Min Act: -0.1700
Data Index: 1717181 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9321. Min Range: -5.9321
Max Act: 5.5571. Min Act: -0.1700
Data Index: 7332080 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19