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

Dataset: The Pile

Neuron 3106 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: 0.9746. Min Range: -0.9746

Max Act: 0.8880. Min Act: -0.0000

Data Index: 176719 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1391797 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9746. Min Act: -0.0000

Data Index: 425730 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9140. Min Act: -0.0000

Data Index: 173433 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1719897 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1393354 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1610190 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1047355 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8088. Min Act: -0.0000

Data Index: 126837 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7982. Min Act: -0.0000

Data Index: 573023 (The Pile)

Max Activating Token Index: 49

Text #10

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7701. Min Act: -0.0000

Data Index: 740941 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1651720 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.6604. Min Act: -0.0000

Data Index: 932797 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7019. Min Act: -0.0000

Data Index: 660245 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1797576 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1315866 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7149. Min Act: -0.0000

Data Index: 536422 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7263. Min Act: -0.0000

Data Index: 205441 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1164247 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7070. Min Act: 0.0000

Data Index: 1079229 (The Pile)

Max Activating Token Index: 81