Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 13.2701. Min Range: -13.2701
Max Act: 13.2701. Min Act: -0.1700
Data Index: 2925873 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.2701. Min Range: -13.2701
Max Act: 13.1451. Min Act: -0.1700
Data Index: 1933492 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.2701. Min Range: -13.2701
Max Act: 13.0201. Min Act: -0.1700
Data Index: 8002501 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.9576. Min Act: -0.1700
Data Index: 4043708 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.7701. Min Act: -0.1700
Data Index: 3852107 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.8326. Min Act: -0.1700
Data Index: 1079325 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.7701. Min Act: -0.1700
Data Index: 1700337 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.7701. Min Act: -0.1700
Data Index: 6192590 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.8326. Min Act: -0.1700
Data Index: 3147578 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.7076. Min Act: -0.1700
Data Index: 3141098 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.7701. Min Act: -0.1700
Data Index: 3555476 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.7076. Min Act: -0.1700
Data Index: 5440066 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.5826. Min Act: -0.1700
Data Index: 7830672 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.5826. Min Act: -0.1700
Data Index: 264655 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.5201. Min Act: -0.1700
Data Index: 395139 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.5826. Min Act: -0.1700
Data Index: 1997700 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.4576. Min Act: -0.1700
Data Index: 7283062 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.5201. Min Act: -0.1700
Data Index: 6892720 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.4576. Min Act: -0.1700
Data Index: 264663 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.2701. Min Range: -13.2701
Max Act: 12.4576. Min Act: -0.1700
Data Index: 3359812 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19