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

Dataset: The Pile

Neuron 1457 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: 0.2228. Min Range: -0.2228

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1920294 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1647516 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1702 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1606. Min Act: -0.0000

Data Index: 105181 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1244333 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1543. Min Act: -0.0000

Data Index: 291055 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1622. Min Act: -0.0000

Data Index: 795228 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1367866 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1357. Min Act: -0.0000

Data Index: 516493 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1443. Min Act: -0.0000

Data Index: 929553 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1349799 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1342. Min Act: -0.0000

Data Index: 959850 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1433. Min Act: -0.0000

Data Index: 65670 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1463. Min Act: -0.0000

Data Index: 548421 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1556568 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1029. Min Act: -0.0000

Data Index: 580294 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1056196 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1171. Min Act: -0.0000

Data Index: 325587 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1750313 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1346880 (The Pile)

Max Activating Token Index: 980