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

Dataset: The Pile

Neuron 1601 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2881. Min Act: -0.0000

Data Index: 859568 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2527. Min Act: -0.0000

Data Index: 879570 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1162571 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1779725 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2539. Min Act: -0.0000

Data Index: 748749 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1276623 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1578261 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2320. Min Act: -0.0000

Data Index: 981978 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1842676 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1690530 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2201. Min Act: -0.0000

Data Index: 354065 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2198. Min Act: -0.0000

Data Index: 654898 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2200. Min Act: -0.0000

Data Index: 317502 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.1820. Min Act: -0.0000

Data Index: 720329 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2105. Min Act: -0.0000

Data Index: 138711 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2072. Min Act: -0.0000

Data Index: 350628 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2149. Min Act: 0.0000

Data Index: 199727 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2150. Min Act: -0.0000

Data Index: 372858 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2085. Min Act: -0.0000

Data Index: 787558 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1613350 (The Pile)

Max Activating Token Index: 916