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

Dataset: The Pile

Neuron 4350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.6126. Min Act: -0.0000

Data Index: 514083 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1660908 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.5759. Min Act: -0.0000

Data Index: 60525 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.6528. Min Act: -0.0000

Data Index: 11747 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1808451 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.3909. Min Act: -0.0000

Data Index: 459101 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.3588. Min Act: -0.0000

Data Index: 508934 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1454845 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.3295. Min Act: -0.0000

Data Index: 511787 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.3756. Min Act: -0.0000

Data Index: 691288 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1776475 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1569098 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1055493 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.2532. Min Act: -0.0000

Data Index: 999474 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1236862 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1766239 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1445267 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.3068. Min Act: -0.0000

Data Index: 10422 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1419262 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.6528. Min Range: -1.6528

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1234975 (The Pile)

Max Activating Token Index: 15