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

Dataset: The Pile

Neuron 353 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: 1.4251. Min Range: -1.4251

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1843509 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.3113. Min Act: -0.0000

Data Index: 289312 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1783743 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.1806. Min Act: -0.0000

Data Index: 279994 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1699059 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.2149. Min Act: -0.0000

Data Index: 453049 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.1548. Min Act: -0.0000

Data Index: 257124 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.1710. Min Act: -0.0000

Data Index: 612658 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.1497. Min Act: -0.0000

Data Index: 649076 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.1078. Min Act: -0.0000

Data Index: 250228 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1483596 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1936850 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0257. Min Act: -0.0000

Data Index: 250268 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0584. Min Act: -0.0000

Data Index: 952770 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1131630 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0041. Min Act: -0.0000

Data Index: 55657 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1261988 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1119537 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1850473 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1683780 (The Pile)

Max Activating Token Index: 456