Model: None
Dataset: The Pile
Neuron 397 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.8437. Min Act: -0.1700
Data Index: 3890901 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.7960. Min Act: -0.1700
Data Index: 1939532 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.7162. Min Act: -0.1700
Data Index: 9268583 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.6682. Min Act: -0.1700
Data Index: 957198 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.6521. Min Act: -0.1700
Data Index: 1314302 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.6361. Min Act: -0.1700
Data Index: 7554824 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5878. Min Act: -0.1700
Data Index: 10165466 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5878. Min Act: -0.1700
Data Index: 5177117 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5878. Min Act: -0.1700
Data Index: 10674187 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5717. Min Act: -0.1700
Data Index: 5644683 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5717. Min Act: -0.1700
Data Index: 4405589 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5717. Min Act: -0.1700
Data Index: 762773 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5556. Min Act: -0.1700
Data Index: 9135616 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5395. Min Act: -0.1700
Data Index: 5380717 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5395. Min Act: -0.1700
Data Index: 1563861 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5395. Min Act: -0.1700
Data Index: 3547015 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5395. Min Act: -0.1700
Data Index: 6450795 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5233. Min Act: -0.1700
Data Index: 386398 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5233. Min Act: -0.1700
Data Index: 790128 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8437. Min Range: -2.8437
Max Act: 2.5233. Min Act: -0.1700
Data Index: 3323340 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19