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

Dataset: The Pile

Neuron 5042 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: 0.8247. Min Range: -0.8247

Max Act: 0.8247. Min Act: -0.0000

Data Index: 376305 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6690. Min Act: -0.0000

Data Index: 594751 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6531. Min Act: -0.0000

Data Index: 881670 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6273. Min Act: -0.0000

Data Index: 484679 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6679. Min Act: -0.0000

Data Index: 274071 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1039106 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6169. Min Act: -0.0000

Data Index: 646294 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6310. Min Act: -0.0000

Data Index: 95891 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1351966 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1102588 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6149. Min Act: -0.0000

Data Index: 553094 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1293880 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1135983 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1833885 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1031985 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5915. Min Act: -0.0000

Data Index: 788668 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5904. Min Act: -0.0000

Data Index: 610687 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5849. Min Act: -0.0000

Data Index: 838992 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5836. Min Act: -0.0000

Data Index: 41009 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.5817. Min Act: -0.0000

Data Index: 952840 (The Pile)

Max Activating Token Index: 556