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

Dataset: The Pile

Neuron 3373 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: 0.0000

Data Index: 1480940 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0237. Min Act: -0.0000

Data Index: 433493 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0223. Min Act: 0.0000

Data Index: 803516 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0232. Min Act: -0.0000

Data Index: 255883 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0220. Min Act: 0.0000

Data Index: 33113 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0216. Min Act: -0.0000

Data Index: 980335 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0215. Min Act: -0.0000

Data Index: 1376162 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1617687 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0212. Min Act: 0.0000

Data Index: 1460662 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0204. Min Act: 0.0000

Data Index: 1279539 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0210. Min Act: 0.0000

Data Index: 426291 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1324330 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0209. Min Act: -0.0000

Data Index: 881533 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0209. Min Act: -0.0000

Data Index: 639083 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0208. Min Act: -0.0000

Data Index: 927991 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0208. Min Act: 0.0000

Data Index: 238988 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1433608 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1559466 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0206. Min Act: -0.0000

Data Index: 1703688 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0205. Min Act: 0.0000

Data Index: 393054 (The Pile)

Max Activating Token Index: 806