Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.4863. Min Act: -0.1700
Data Index: 761613 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.4237. Min Act: -0.1700
Data Index: 7858121 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.3296. Min Act: -0.1700
Data Index: 2028306 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2982. Min Act: -0.1700
Data Index: 669561 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2668. Min Act: -0.1700
Data Index: 7869922 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2511. Min Act: -0.1700
Data Index: 3845425 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2196. Min Act: -0.1700
Data Index: 5750998 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2039. Min Act: -0.1700
Data Index: 8107814 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1882. Min Act: -0.1700
Data Index: 4988652 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1567. Min Act: -0.1700
Data Index: 2866441 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2196. Min Act: -0.1700
Data Index: 4911840 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1567. Min Act: -0.1700
Data Index: 8306026 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.2196. Min Act: -0.1700
Data Index: 8351804 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1724. Min Act: -0.1700
Data Index: 5389297 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1567. Min Act: -0.1700
Data Index: 898346 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1252. Min Act: -0.1700
Data Index: 3095701 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.1095. Min Act: -0.1700
Data Index: 2164423 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.0779. Min Act: -0.1700
Data Index: 621778 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.0937. Min Act: -0.1700
Data Index: 6284496 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4863. Min Range: -3.4863
Max Act: 3.0937. Min Act: -0.1700
Data Index: 4461749 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19