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

Dataset: The Pile

Neuron 1967 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: 0.9539. Min Range: -0.9539

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1671736 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1677064 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1684146 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7500. Min Act: -0.0000

Data Index: 314697 (The Pile)

Max Activating Token Index: 479

Text #4

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8173. Min Act: -0.0000

Data Index: 508086 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1649942 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8128. Min Act: -0.0000

Data Index: 95036 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1492805 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8239. Min Act: 0.0000

Data Index: 1630631 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8329. Min Act: -0.0000

Data Index: 942930 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1177951 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8163. Min Act: -0.0000

Data Index: 851952 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1841008 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1577402 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1854391 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1842963 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1174948 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6904. Min Act: -0.0000

Data Index: 553785 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7868. Min Act: -0.0000

Data Index: 582501 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7691. Min Act: -0.0000

Data Index: 552540 (The Pile)

Max Activating Token Index: 595