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

Dataset: The Pile

Neuron 4330 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: 0.9245. Min Range: -0.9245

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1591588 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1783947 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1973816 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9235. Min Act: -0.0000

Data Index: 179647 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9200. Min Act: 0.0000

Data Index: 778297 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8541. Min Act: -0.0000

Data Index: 965908 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7668. Min Act: -0.0000

Data Index: 297207 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1081632 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7672. Min Act: -0.0000

Data Index: 921361 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1362344 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1083497 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7483. Min Act: -0.0000

Data Index: 965506 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7727. Min Act: 0.0001

Data Index: 1445276 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1172621 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1709621 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7400. Min Act: -0.0000

Data Index: 437153 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6906. Min Act: -0.0000

Data Index: 964463 (The Pile)

Max Activating Token Index: 379

Text #17

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1168903 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1060816 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1997114 (The Pile)

Max Activating Token Index: 781