Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7855. Min Act: -0.1700
Data Index: 4406063 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7536. Min Act: -0.1700
Data Index: 326431 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7376. Min Act: -0.1700
Data Index: 1508576 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7536. Min Act: -0.1700
Data Index: 2533902 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7376. Min Act: -0.1700
Data Index: 1001419 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7376. Min Act: -0.1700
Data Index: 5445005 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7376. Min Act: -0.1700
Data Index: 191590 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7376. Min Act: -0.1700
Data Index: 4312708 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7216. Min Act: -0.1700
Data Index: 6591769 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7057. Min Act: -0.1700
Data Index: 7001226 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7216. Min Act: -0.1700
Data Index: 7547137 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7216. Min Act: -0.1700
Data Index: 3421335 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7216. Min Act: -0.1700
Data Index: 8678056 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7216. Min Act: -0.1700
Data Index: 1006924 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.6897. Min Act: -0.1700
Data Index: 6025566 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7057. Min Act: -0.1700
Data Index: 7103386 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7057. Min Act: -0.1700
Data Index: 8534515 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7057. Min Act: -0.1700
Data Index: 169922 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.7057. Min Act: -0.1700
Data Index: 994881 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7855. Min Range: -2.7855
Max Act: 2.6897. Min Act: -0.1700
Data Index: 868912 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19