Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1184261 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1265. Min Act: -0.0001

Data Index: 652665 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1330. Min Act: -0.0001

Data Index: 365142 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1397. Min Act: -0.0001

Data Index: 582303 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1316. Min Act: -0.0001

Data Index: 646095 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1244. Min Act: -0.0001

Data Index: 934908 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1063661 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1246. Min Act: -0.0001

Data Index: 347759 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1195255 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1237. Min Act: -0.0001

Data Index: 226437 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1228. Min Act: -0.0001

Data Index: 717962 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1214. Min Act: -0.0001

Data Index: 290021 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1263. Min Act: -0.0001

Data Index: 129659 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1221552 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1197. Min Act: -0.0001

Data Index: 497158 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1186. Min Act: -0.0001

Data Index: 804212 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1241. Min Act: -0.0001

Data Index: 69703 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1179. Min Act: -0.0001

Data Index: 136280 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1107325 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1006420 (C4 (Web Text))

Max Activating Token Index: 64