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

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

Neuron 1424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1156338 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1223. Min Act: -0.0002

Data Index: 521817 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1523808 (Python Code)

Max Activating Token Index: 639

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1456153 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1207. Min Act: -0.0001

Data Index: 968124 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1247. Min Act: -0.0002

Data Index: 94769 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1425572 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1174. Min Act: -0.0002

Data Index: 197634 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1597997 (Python Code)

Max Activating Token Index: 472

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1121. Min Act: -0.0002

Data Index: 528971 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1579181 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1492305 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1117. Min Act: -0.0001

Data Index: 983343 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1588778 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1409347 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1293359 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1615377 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1623704 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1505828 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1115. Min Act: -0.0002

Data Index: 46479 (C4 (Web Text))

Max Activating Token Index: 414