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

Dataset: The Pile

Neuron 3373 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4059. Min Act: -0.0000

Data Index: 457627 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2588. Min Act: -0.0000

Data Index: 490805 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2582. Min Act: -0.0000

Data Index: 952591 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2593. Min Act: -0.0000

Data Index: 86275 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1793171 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1779556 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2391. Min Act: -0.0000

Data Index: 443360 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1923884 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2401. Min Act: -0.0000

Data Index: 941949 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1647359 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2178. Min Act: -0.0000

Data Index: 591547 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2365. Min Act: -0.0000

Data Index: 905677 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1730521 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2202. Min Act: 0.0000

Data Index: 958328 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1102339 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1976944 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.1874. Min Act: -0.0000

Data Index: 20624 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1138106 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1325377 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2131. Min Act: -0.0000

Data Index: 487369 (The Pile)

Max Activating Token Index: 435