Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0000

Data Index: 45270 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2445. Min Act: -0.0000

Data Index: 502074 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2002. Min Act: -0.0000

Data Index: 668988 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1983635 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1928. Min Act: -0.0000

Data Index: 766206 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1571079 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2747. Min Act: -0.0000

Data Index: 666621 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1497868 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2148. Min Act: -0.0000

Data Index: 393705 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1966. Min Act: -0.0000

Data Index: 948604 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2036. Min Act: -0.0000

Data Index: 77501 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2255. Min Act: -0.0000

Data Index: 422569 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1985582 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1024902 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2183. Min Act: -0.0000

Data Index: 903224 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1332043 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1687781 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2724. Min Act: -0.0000

Data Index: 98331 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1335756 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1924. Min Act: -0.0000

Data Index: 828414 (The Pile)

Max Activating Token Index: 545