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

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

Neuron 808 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1669. Min Act: -0.0000

Data Index: 984310 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1346889 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1592. Min Act: -0.0000

Data Index: 102190 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1666. Min Act: -0.0000

Data Index: 219699 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1546. Min Act: -0.0000

Data Index: 497960 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1549. Min Act: -0.0000

Data Index: 336986 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1024353 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1339. Min Act: -0.0000

Data Index: 798324 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1245. Min Act: -0.0000

Data Index: 954691 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1260. Min Act: -0.0000

Data Index: 10131 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1211. Min Act: -0.0000

Data Index: 265379 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1164688 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1272. Min Act: -0.0000

Data Index: 103203 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1109153 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1060639 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1196. Min Act: -0.0000

Data Index: 357285 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1075. Min Act: -0.0000

Data Index: 86885 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1197. Min Act: -0.0000

Data Index: 851220 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1148. Min Act: -0.0000

Data Index: 508334 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1141. Min Act: -0.0000

Data Index: 170180 (C4 (Web Text))

Max Activating Token Index: 221