Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3332. Min Range: -8.3332
Max Act: 8.3332. Min Act: -0.1700
Data Index: 8448481 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3332. Min Range: -8.3332
Max Act: 8.2707. Min Act: -0.1700
Data Index: 3235764 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3332. Min Range: -8.3332
Max Act: 8.0520. Min Act: -0.1700
Data Index: 6243573 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.8957. Min Act: -0.1700
Data Index: 6070330 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.8020. Min Act: -0.1700
Data Index: 868948 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.7707. Min Act: -0.1700
Data Index: 1856531 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.7082. Min Act: -0.1700
Data Index: 8607718 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.7082. Min Act: -0.1700
Data Index: 7212531 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.7082. Min Act: -0.1700
Data Index: 741918 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.6770. Min Act: -0.1700
Data Index: 7953596 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.6457. Min Act: -0.1700
Data Index: 6657295 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.6457. Min Act: -0.1700
Data Index: 2965285 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.6457. Min Act: -0.1700
Data Index: 3875498 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.5520. Min Act: -0.1700
Data Index: 6449099 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.4895. Min Act: -0.1700
Data Index: 4828933 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.5520. Min Act: -0.1700
Data Index: 268078 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.5207. Min Act: -0.1700
Data Index: 2038201 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.4895. Min Act: -0.1700
Data Index: 3210768 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.4895. Min Act: -0.1700
Data Index: 4178231 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3332. Min Range: -8.3332
Max Act: 7.4582. Min Act: -0.1700
Data Index: 8493837 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19