Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4978. Min Range: -9.4978
Max Act: 9.4978. Min Act: -0.1700
Data Index: 3847967 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4978. Min Range: -9.4978
Max Act: 9.3728. Min Act: -0.1700
Data Index: 1328363 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.9978. Min Act: -0.1700
Data Index: 4300960 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.4978. Min Act: -0.1700
Data Index: 6849809 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.3728. Min Act: -0.1700
Data Index: 1881683 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.3103. Min Act: -0.1700
Data Index: 7953654 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.2478. Min Act: -0.1700
Data Index: 1415239 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.1853. Min Act: -0.1700
Data Index: 1225652 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.2478. Min Act: -0.1700
Data Index: 732036 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.0603. Min Act: -0.1700
Data Index: 1641415 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4978. Min Range: -9.4978
Max Act: 8.0603. Min Act: -0.1700
Data Index: 4971375 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.9978. Min Act: -0.1700
Data Index: 2385941 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.9978. Min Act: -0.1700
Data Index: 4038515 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.9353. Min Act: -0.1700
Data Index: 6272545 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.9353. Min Act: -0.1700
Data Index: 8000084 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.8728. Min Act: -0.1700
Data Index: 6821951 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.8416. Min Act: -0.1700
Data Index: 8111456 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.8416. Min Act: -0.1700
Data Index: 3294401 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.8103. Min Act: -0.1700
Data Index: 5071746 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4978. Min Range: -9.4978
Max Act: 7.7791. Min Act: -0.1700
Data Index: 2184133 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19