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

Dataset: The Pile

Neuron 4312 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: 0.1294. Min Range: -0.1294

Max Act: 0.1282. Min Act: -0.0000

Data Index: 389127 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1267. Min Act: -0.0000

Data Index: 911941 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1294. Min Act: -0.0000

Data Index: 512791 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1237. Min Act: -0.0000

Data Index: 146640 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1226. Min Act: -0.0000

Data Index: 463612 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1166. Min Act: -0.0000

Data Index: 998044 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1113. Min Act: -0.0000

Data Index: 345896 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1599520 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1191. Min Act: -0.0000

Data Index: 680425 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1166. Min Act: -0.0000

Data Index: 74710 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1476859 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1256161 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1155. Min Act: -0.0000

Data Index: 302006 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1759139 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1187. Min Act: -0.0000

Data Index: 890421 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1076. Min Act: -0.0000

Data Index: 148383 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1836084 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1149. Min Act: -0.0000

Data Index: 561213 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1176. Min Act: -0.0000

Data Index: 417978 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1485958 (The Pile)

Max Activating Token Index: 701