Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3293 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1190074 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.3355. Min Act: -0.0000

Data Index: 63039 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.3802. Min Act: -0.0000

Data Index: 340529 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1753794 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1355. Min Act: -0.0000

Data Index: 868771 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1253574 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1867070 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1964179 (The Pile)

Max Activating Token Index: 285

Text #8

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1684154 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1881715 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1667288 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0043. Min Act: -0.0000

Data Index: 471608 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0083. Min Act: 0.0001

Data Index: 314413 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1734251 (The Pile)

Max Activating Token Index: 498

Text #14

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.8406. Min Act: -0.0000

Data Index: 396436 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0067. Min Act: 0.0000

Data Index: 1479629 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1933172 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1120108 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1983425 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.8658. Min Act: -0.0000

Data Index: 840429 (The Pile)

Max Activating Token Index: 70