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

Dataset: The Pile

Neuron 6 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1292269 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2930. Min Act: -0.0000

Data Index: 835894 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1911681 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1261. Min Act: 0.0000

Data Index: 1226542 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1056065 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.0271. Min Act: -0.0000

Data Index: 284643 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1187. Min Act: -0.0000

Data Index: 198941 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1022. Min Act: 0.0000

Data Index: 457194 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1150772 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9989. Min Act: 0.0000

Data Index: 342356 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1521900 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1450698 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.8591. Min Act: 0.0000

Data Index: 1646549 (The Pile)

Max Activating Token Index: 251

Text #13

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1536224 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1270339 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.8990. Min Act: -0.0000

Data Index: 385257 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9378. Min Act: 0.0000

Data Index: 521118 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1527713 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.8676. Min Act: -0.0000

Data Index: 324507 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1651519 (The Pile)

Max Activating Token Index: 664