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

Dataset: The Pile

Neuron 4906 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2358. Min Act: -0.0000

Data Index: 832672 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1917. Min Act: -0.0000

Data Index: 510745 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1127344 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1701. Min Act: -0.0000

Data Index: 576053 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1449. Min Act: -0.0000

Data Index: 14799 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1660713 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1466. Min Act: -0.0000

Data Index: 569904 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1500876 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1362505 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1165. Min Act: -0.0000

Data Index: 184979 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1283. Min Act: -0.0000

Data Index: 289164 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1116. Min Act: -0.0000

Data Index: 10036 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1191. Min Act: -0.0000

Data Index: 551523 (The Pile)

Max Activating Token Index: 718

Text #13

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1111. Min Act: -0.0000

Data Index: 147858 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1216956 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1127. Min Act: -0.0000

Data Index: 752719 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1112. Min Act: -0.0000

Data Index: 548855 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1138747 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1524274 (The Pile)

Max Activating Token Index: 960

Text #19

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1720962 (The Pile)

Max Activating Token Index: 725