Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1575 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.9766. Min Act: -0.0001
Data Index: 213240 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.8693. Min Act: -0.0001
Data Index: 1890356 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.8457. Min Act: -0.0001
Data Index: 1690606 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.8457. Min Act: -0.0001
Data Index: 1632002 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.8457. Min Act: -0.0001
Data Index: 10016 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.7005. Min Act: -0.0001
Data Index: 105586 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6725. Min Act: -0.0001
Data Index: 723464 (The Pile)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6827. Min Act: -0.0001
Data Index: 231876 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6829. Min Act: -0.0001
Data Index: 704017 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.4719. Min Act: -0.0001
Data Index: 259466 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6245. Min Act: -0.0001
Data Index: 1481121 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.8007. Min Act: -0.0001
Data Index: 854435 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.7186. Min Act: -0.0001
Data Index: 1728773 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6621. Min Act: -0.0001
Data Index: 951678 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6621. Min Act: -0.0001
Data Index: 1483639 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6621. Min Act: -0.0001
Data Index: 832549 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.6002. Min Act: -0.0001
Data Index: 1889789 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.3573. Min Act: -0.0001
Data Index: 270773 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.4470. Min Act: -0.0001
Data Index: 1131866 (The Pile)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9766. Min Range: -2.9766
Max Act: 2.4589. Min Act: -0.0001
Data Index: 5491 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19