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

Dataset: The Pile

Neuron 2556 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.7026. Min Act: -0.0000

Data Index: 533531 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6866. Min Act: -0.0000

Data Index: 86978 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6658. Min Act: -0.0000

Data Index: 919733 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6616. Min Act: -0.0000

Data Index: 84073 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6047. Min Act: -0.0000

Data Index: 39529 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5977. Min Act: -0.0000

Data Index: 641187 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5770. Min Act: -0.0000

Data Index: 981243 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1967775 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1124809 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1992366 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1072518 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5454. Min Act: -0.0000

Data Index: 279954 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5214. Min Act: -0.0000

Data Index: 399383 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1179247 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1449310 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6169. Min Act: -0.0000

Data Index: 275825 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1186642 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5063. Min Act: -0.0000

Data Index: 28858 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5322. Min Act: -0.0000

Data Index: 898997 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1282844 (The Pile)

Max Activating Token Index: 924