Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.5234. Min Act: -0.1700
Data Index: 8516565 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.4748. Min Act: -0.1700
Data Index: 4767812 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.4585. Min Act: -0.1700
Data Index: 6553005 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.4097. Min Act: -0.1700
Data Index: 6600895 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.4260. Min Act: -0.1700
Data Index: 8811081 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.4260. Min Act: -0.1700
Data Index: 3657515 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.4260. Min Act: -0.1700
Data Index: 1874342 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3770. Min Act: -0.1700
Data Index: 2499983 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3934. Min Act: -0.1700
Data Index: 1626683 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 254688 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 254689 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3443. Min Act: -0.1700
Data Index: 1435646 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 2900329 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 2742894 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 7565112 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 2681412 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 3786875 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 3774282 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 7427249 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5234. Min Range: -2.5234
Max Act: 2.3607. Min Act: -0.1700
Data Index: 6969714 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19