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

Dataset: The Pile

Neuron 1247 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.3443. Min Act: -0.0000

Data Index: 1485191 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.3843. Min Act: -0.0000

Data Index: 890959 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1046608 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1870269 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1103. Min Act: -0.0000

Data Index: 741064 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1060343 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1811701 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1218171 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1023777 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0186. Min Act: -0.0000

Data Index: 738883 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0945. Min Act: -0.0000

Data Index: 456250 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9837. Min Act: -0.0000

Data Index: 234762 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0299. Min Act: -0.0000

Data Index: 279364 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1505682 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1659839 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1248773 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1353454 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1399. Min Act: -0.0000

Data Index: 476884 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9950. Min Act: -0.0000

Data Index: 582440 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8770. Min Act: -0.0000

Data Index: 295330 (The Pile)

Max Activating Token Index: 440