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

Dataset: The Pile

Neuron 3028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.6370. Min Act: -0.0000

Data Index: 700908 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1853099 (The Pile)

Max Activating Token Index: 674

Text #2

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5960. Min Act: -0.0000

Data Index: 135268 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.6250. Min Act: -0.0000

Data Index: 767093 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5382. Min Act: -0.0000

Data Index: 610892 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1801297 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1757584 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1869121 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1636422 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4961. Min Act: -0.0000

Data Index: 206196 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4735. Min Act: -0.0000

Data Index: 395700 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4959. Min Act: 0.0000

Data Index: 330323 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1005863 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1597016 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4711. Min Act: -0.0000

Data Index: 728406 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1238857 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4259. Min Act: -0.0000

Data Index: 310258 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4304. Min Act: -0.0000

Data Index: 383370 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1870053 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1746289 (The Pile)

Max Activating Token Index: 232