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

Dataset: The Pile

Neuron 2542 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2682. Min Act: -0.0000

Data Index: 340617 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1846958 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2010. Min Act: -0.0000

Data Index: 898251 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2115. Min Act: -0.0000

Data Index: 108228 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1985. Min Act: -0.0000

Data Index: 834034 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1903. Min Act: -0.0000

Data Index: 549515 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1978. Min Act: -0.0000

Data Index: 567241 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1921. Min Act: -0.0000

Data Index: 498757 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1193967 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1156174 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1744. Min Act: -0.0000

Data Index: 751685 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1692. Min Act: -0.0000

Data Index: 387987 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1752. Min Act: -0.0000

Data Index: 408599 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1578. Min Act: -0.0000

Data Index: 35627 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1571. Min Act: 0.0000

Data Index: 1551880 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1632357 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1811. Min Act: -0.0000

Data Index: 21535 (The Pile)

Max Activating Token Index: 581