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

Dataset: The Pile

Neuron 991 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: 0.1396. Min Range: -0.1396

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1860954 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1991821 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1239. Min Act: -0.0000

Data Index: 598827 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1267. Min Act: -0.0000

Data Index: 991565 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1298. Min Act: -0.0000

Data Index: 758989 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1523262 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1195. Min Act: -0.0000

Data Index: 986597 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1978187 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1307885 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1767184 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1178. Min Act: -0.0000

Data Index: 81434 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1303801 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1223091 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1197. Min Act: -0.0000

Data Index: 161853 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1447748 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1855903 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1061. Min Act: -0.0000

Data Index: 888207 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1224. Min Act: -0.0000

Data Index: 243197 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1127. Min Act: -0.0000

Data Index: 567985 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1206. Min Act: -0.0000

Data Index: 262202 (The Pile)

Max Activating Token Index: 679