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

Dataset: The Pile

Neuron 3943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1785. Min Act: -0.0000

Data Index: 320809 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1897. Min Act: -0.0000

Data Index: 240171 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1573655 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1581. Min Act: -0.0000

Data Index: 859940 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1242963 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1264. Min Act: -0.0000

Data Index: 904417 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1188951 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1143. Min Act: -0.0000

Data Index: 276634 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1326. Min Act: -0.0000

Data Index: 160950 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1777967 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1210153 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1888352 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1141. Min Act: -0.0000

Data Index: 9697 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1159. Min Act: -0.0000

Data Index: 371099 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1074651 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1541615 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1418189 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1314. Min Act: -0.0000

Data Index: 281031 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1465779 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1176. Min Act: -0.0000

Data Index: 503720 (The Pile)

Max Activating Token Index: 717