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

Dataset: The Pile

Neuron 3649 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: 0.1744. Min Range: -0.1744

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1841362 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0000

Data Index: 517566 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1576. Min Act: -0.0000

Data Index: 123286 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1228668 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1987697 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1679821 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1411. Min Act: -0.0000

Data Index: 322328 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1358. Min Act: -0.0000

Data Index: 177356 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1264. Min Act: -0.0000

Data Index: 785207 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1001069 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1308. Min Act: -0.0000

Data Index: 173801 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1797122 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1718853 (The Pile)

Max Activating Token Index: 845

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1246572 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1647286 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1137. Min Act: -0.0000

Data Index: 465676 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1186633 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1034. Min Act: -0.0000

Data Index: 74425 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1687680 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1495149 (The Pile)

Max Activating Token Index: 1018