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

Dataset: The Pile

Neuron 1596 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.5421. Min Act: -0.0000

Data Index: 659859 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.5227. Min Act: -0.0000

Data Index: 1187198 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.5209. Min Act: -0.0000

Data Index: 1943217 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4864. Min Act: -0.0000

Data Index: 314988 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4688. Min Act: -0.0000

Data Index: 680517 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4132. Min Act: -0.0000

Data Index: 905230 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4980. Min Act: -0.0000

Data Index: 806166 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4581. Min Act: -0.0000

Data Index: 928659 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1078630 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1476559 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.3029. Min Act: -0.0000

Data Index: 1989531 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2426. Min Act: -0.0000

Data Index: 491365 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2840. Min Act: -0.0000

Data Index: 428257 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1304398 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1477843 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2684. Min Act: -0.0000

Data Index: 518265 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1347454 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.1063. Min Act: -0.0000

Data Index: 852499 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.5421. Min Range: -1.5421

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1815240 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 1.5421. Min Range: -1.5421

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1185116 (The Pile)

Max Activating Token Index: 86