Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.4789. Min Act: -0.1700
Data Index: 6624641 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.4477. Min Act: -0.1700
Data Index: 7350547 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.4164. Min Act: -0.1700
Data Index: 5018913 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.4164. Min Act: -0.1700
Data Index: 5240843 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.3539. Min Act: -0.1700
Data Index: 7422794 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.3227. Min Act: -0.1700
Data Index: 3649659 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.2602. Min Act: -0.1700
Data Index: 925062 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.2602. Min Act: -0.1700
Data Index: 3429709 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.2289. Min Act: -0.1700
Data Index: 5022147 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.2289. Min Act: -0.1700
Data Index: 7093516 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1977. Min Act: -0.1700
Data Index: 7558462 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1977. Min Act: -0.1700
Data Index: 3841432 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1664. Min Act: -0.1700
Data Index: 8381719 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6026966 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1352. Min Act: -0.1700
Data Index: 1874970 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1039. Min Act: -0.1700
Data Index: 4502963 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1039. Min Act: -0.1700
Data Index: 1746538 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1039. Min Act: -0.1700
Data Index: 7800935 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.1039. Min Act: -0.1700
Data Index: 4084653 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4789. Min Range: -7.4789
Max Act: 7.0727. Min Act: -0.1700
Data Index: 5272365 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19