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

Dataset: The Pile

Neuron 4355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1370882 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1621969 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1825974 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1937317 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1209900 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1729010 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1164887 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1510105 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1646840 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1163. Min Act: -0.0000

Data Index: 1868698 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1808041 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1264812 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1442742 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1016133 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1131911 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1187. Min Act: -0.0000

Data Index: 34115 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1178. Min Act: -0.0000

Data Index: 807217 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1425045 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1219. Min Act: -0.0000

Data Index: 637009 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.1578. Min Range: -0.1578

Max Act: 0.1210. Min Act: -0.0000

Data Index: 568666 (The Pile)

Max Activating Token Index: 112