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

Dataset: The Pile

Neuron 2257 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: 1.6184. Min Range: -1.6184

Max Act: 1.6184. Min Act: -0.0000

Data Index: 904389 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.5743. Min Act: -0.0000

Data Index: 1509546 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1891626 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.4132. Min Act: -0.0000

Data Index: 750518 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1947108 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.4223. Min Act: -0.0000

Data Index: 157549 (The Pile)

Max Activating Token Index: 474

Text #6

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1668152 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.3828. Min Act: -0.0000

Data Index: 59400 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1741962 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1064304 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.4296. Min Act: -0.0000

Data Index: 721531 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1490164 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1581765 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1070133 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.1941. Min Act: -0.0000

Data Index: 1790003 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1157633 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.1817. Min Act: -0.0000

Data Index: 94185 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.1751. Min Act: -0.0000

Data Index: 200369 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2255. Min Act: -0.0000

Data Index: 77107 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1681544 (The Pile)

Max Activating Token Index: 166