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

Dataset: The Pile

Neuron 1600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1108406 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1270652 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2451. Min Act: -0.0000

Data Index: 826712 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1880. Min Act: -0.0000

Data Index: 192798 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2852. Min Act: -0.0000

Data Index: 312103 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1487294 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2328. Min Act: -0.0000

Data Index: 975931 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1717104 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1307773 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1691416 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1274281 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2103. Min Act: -0.0000

Data Index: 907540 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1060854 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1497462 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1020436 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1898. Min Act: -0.0000

Data Index: 384492 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2204. Min Act: -0.0000

Data Index: 621876 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2111. Min Act: -0.0000

Data Index: 932288 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1952. Min Act: -0.0000

Data Index: 275614 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2085. Min Act: -0.0000

Data Index: 846763 (The Pile)

Max Activating Token Index: 348