Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3113 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.8720. Min Act: -0.1700
Data Index: 1199623 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.8465. Min Act: -0.1700
Data Index: 2873749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.8381. Min Act: -0.1700
Data Index: 8724307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.8296. Min Act: -0.1700
Data Index: 3218694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7960. Min Act: -0.1700
Data Index: 339200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7960. Min Act: -0.1700
Data Index: 994391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7960. Min Act: -0.1700
Data Index: 3076690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7876. Min Act: -0.1700
Data Index: 2375809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7876. Min Act: -0.1700
Data Index: 8126480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7876. Min Act: -0.1700
Data Index: 2351867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7709. Min Act: -0.1700
Data Index: 6758488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7709. Min Act: -0.1700
Data Index: 3067113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7793. Min Act: -0.1700
Data Index: 7502621 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7709. Min Act: -0.1700
Data Index: 1482950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7709. Min Act: -0.1700
Data Index: 6422454 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7709. Min Act: -0.1700
Data Index: 4622894 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7543. Min Act: -0.1700
Data Index: 3931897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7543. Min Act: -0.1700
Data Index: 3961703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7543. Min Act: -0.1700
Data Index: 2346902 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8720. Min Range: -0.8720
Max Act: 0.7626. Min Act: -0.1700
Data Index: 4136386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19