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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3667 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1561117 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2383. Min Act: -0.0000

Data Index: 150858 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2517. Min Act: -0.0000

Data Index: 827511 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1642307 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2310. Min Act: -0.0000

Data Index: 17784 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1111951 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1961. Min Act: -0.0000

Data Index: 976871 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1598233 (Python Code)

Max Activating Token Index: 415

Text #8

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1598943 (Python Code)

Max Activating Token Index: 656

Text #9

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1717. Min Act: -0.0000

Data Index: 101192 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1516542 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1421940 (Python Code)

Max Activating Token Index: 268

Text #12

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1774. Min Act: -0.0000

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1109147 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1563306 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1432181 (Python Code)

Max Activating Token Index: 990

Text #16

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1558573 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1649. Min Act: -0.0000

Data Index: 700737 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1631720 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1620. Min Act: -0.0000

Data Index: 432030 (C4 (Web Text))

Max Activating Token Index: 324