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

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

Neuron 3307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1569. Min Act: -0.0002

Data Index: 825648 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1402. Min Act: -0.0002

Data Index: 205225 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1218. Min Act: -0.0002

Data Index: 1085258 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1055641 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1252. Min Act: -0.0002

Data Index: 821480 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1205. Min Act: -0.0002

Data Index: 507511 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1273. Min Act: -0.0002

Data Index: 423260 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1229120 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1261805 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1172. Min Act: -0.0002

Data Index: 151893 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1097. Min Act: -0.0002

Data Index: 403896 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1155611 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1194173 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1247. Min Act: -0.0002

Data Index: 1339960 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1039. Min Act: -0.0002

Data Index: 939176 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1122. Min Act: -0.0002

Data Index: 205485 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1127. Min Act: -0.0002

Data Index: 285180 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1030859 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1173. Min Act: -0.0002

Data Index: 715097 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1209260 (C4 (Web Text))

Max Activating Token Index: 9