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

Dataset: The Pile

Neuron 3119 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: 0.1296. Min Range: -0.1296

Max Act: 0.1275. Min Act: -0.0000

Data Index: 276516 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1039622 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1295103 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1167. Min Act: -0.0000

Data Index: 449836 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1053. Min Act: -0.0000

Data Index: 318170 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1508126 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1625700 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1171490 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1084. Min Act: -0.0000

Data Index: 842601 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1978129 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1013887 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1047. Min Act: -0.0000

Data Index: 2404 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0893. Min Act: -0.0000

Data Index: 652931 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1024. Min Act: -0.0000

Data Index: 446298 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1166660 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0584. Min Act: -0.0000

Data Index: 759622 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0984. Min Act: -0.0000

Data Index: 406623 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1497521 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0795. Min Act: -0.0000

Data Index: 157440 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0783. Min Act: -0.0000

Data Index: 569929 (The Pile)

Max Activating Token Index: 959