Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 506 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.8507. Min Act: -0.0000

Data Index: 928589 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.8069. Min Act: -0.0000

Data Index: 153573 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7770. Min Act: -0.0000

Data Index: 780914 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1264565 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1371416 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1025090 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1427592 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1905686 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6825. Min Act: -0.0000

Data Index: 49188 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7192. Min Act: -0.0000

Data Index: 388025 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7019. Min Act: -0.0000

Data Index: 900411 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7210. Min Act: -0.0000

Data Index: 101754 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6669. Min Act: -0.0000

Data Index: 771127 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1572705 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6908. Min Act: -0.0000

Data Index: 731323 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1770883 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7024. Min Act: -0.0000

Data Index: 341354 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6641. Min Act: -0.0000

Data Index: 959532 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1806946 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6487. Min Act: -0.0000

Data Index: 7868 (The Pile)

Max Activating Token Index: 940