Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.5365. Min Act: -0.1700
Data Index: 2243454 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.5209. Min Act: -0.1700
Data Index: 7009010 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.5052. Min Act: -0.1700
Data Index: 5758737 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4582. Min Act: -0.1700
Data Index: 2959043 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4425. Min Act: -0.1700
Data Index: 8643179 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4425. Min Act: -0.1700
Data Index: 3004582 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4425. Min Act: -0.1700
Data Index: 971086 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4582. Min Act: -0.1700
Data Index: 7909985 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4269. Min Act: -0.1700
Data Index: 4364505 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4269. Min Act: -0.1700
Data Index: 2745806 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4112. Min Act: -0.1700
Data Index: 513391 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.3955. Min Act: -0.1700
Data Index: 1083789 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4112. Min Act: -0.1700
Data Index: 3177801 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.3955. Min Act: -0.1700
Data Index: 8457816 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.3955. Min Act: -0.1700
Data Index: 2545383 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4112. Min Act: -0.1700
Data Index: 7572644 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.4112. Min Act: -0.1700
Data Index: 2652466 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.3798. Min Act: -0.1700
Data Index: 1856966 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.3642. Min Act: -0.1700
Data Index: 2236039 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.3642. Min Act: -0.1700
Data Index: 7300110 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19