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

Dataset: The Pile

Neuron 2529 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: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0000

Data Index: 366449 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1362857 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1434530 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1990660 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1770116 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1284. Min Act: -0.0000

Data Index: 360181 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1279. Min Act: -0.0000

Data Index: 954619 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1345. Min Act: 0.0000

Data Index: 320225 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1872618 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1411593 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1225. Min Act: -0.0000

Data Index: 520861 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1566855 (The Pile)

Max Activating Token Index: 95

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1766855 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1125. Min Act: -0.0000

Data Index: 607811 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1031. Min Act: -0.0000

Data Index: 699953 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1578958 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1521007 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1119. Min Act: -0.0000

Data Index: 876204 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1590250 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1629720 (The Pile)

Max Activating Token Index: 865