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

Dataset: The Pile

Neuron 2178 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: 1.5272. Min Range: -1.5272

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1010970 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2534. Min Act: -0.0000

Data Index: 395313 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1838970 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.3064. Min Act: -0.0000

Data Index: 1498160 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2198. Min Act: -0.0000

Data Index: 387022 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1504704 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1932. Min Act: -0.0000

Data Index: 305974 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1833. Min Act: -0.0000

Data Index: 710244 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2350. Min Act: -0.0000

Data Index: 726144 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2149. Min Act: -0.0000

Data Index: 339698 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1845024 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1416073 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1810938 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1192960 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1269522 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1063412 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1497. Min Act: -0.0000

Data Index: 748272 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1566785 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0516. Min Act: -0.0000

Data Index: 710632 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0390. Min Act: -0.0000

Data Index: 982290 (The Pile)

Max Activating Token Index: 415