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

Dataset: The Pile

Neuron 3864 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: 0.1490. Min Range: -0.1490

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1990394 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1267. Min Act: -0.0000

Data Index: 71004 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1393. Min Act: -0.0001

Data Index: 546674 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1324. Min Act: -0.0000

Data Index: 960895 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1218. Min Act: -0.0000

Data Index: 163460 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1196. Min Act: -0.0000

Data Index: 600578 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1402029 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1263475 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1559472 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1422539 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1682286 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1122. Min Act: -0.0000

Data Index: 986272 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1637169 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1442320 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1156. Min Act: -0.0000

Data Index: 967526 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1049643 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1372170 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1083. Min Act: -0.0000

Data Index: 439453 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1009958 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0960. Min Act: -0.0000

Data Index: 29566 (The Pile)

Max Activating Token Index: 302