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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3578 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1345081 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1568182 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1486966 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1482832 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1188. Min Act: -0.0000

Data Index: 230686 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1533177 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1541614 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1566800 (Python Code)

Max Activating Token Index: 479

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1210. Min Act: -0.0000

Data Index: 269021 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1163. Min Act: 0.0000

Data Index: 1630768 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1399960 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1426664 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1656464 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1631215 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1607213 (Python Code)

Max Activating Token Index: 705

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1220. Min Act: -0.0000

Data Index: 177186 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1649325 (Python Code)

Max Activating Token Index: 709

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1365611 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1374821 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1646211 (Python Code)

Max Activating Token Index: 123