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

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

Neuron 439 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: 0.1476. Min Range: -0.1476

Max Act: 0.1476. Min Act: -0.0002

Data Index: 346142 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1442. Min Act: -0.0001

Data Index: 151397 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1078439 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1311. Min Act: -0.0002

Data Index: 225310 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1231297 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1319. Min Act: -0.0001

Data Index: 475632 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1267. Min Act: -0.0002

Data Index: 308861 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1307. Min Act: -0.0001

Data Index: 202156 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1252467 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1302. Min Act: -0.0002

Data Index: 505386 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1250. Min Act: -0.0002

Data Index: 622458 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1250. Min Act: -0.0001

Data Index: 729916 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1267. Min Act: -0.0001

Data Index: 157889 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1141641 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1355112 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1172. Min Act: -0.0001

Data Index: 787628 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1283. Min Act: -0.0002

Data Index: 454187 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1156437 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1172. Min Act: -0.0001

Data Index: 760813 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1244. Min Act: -0.0001

Data Index: 607045 (C4 (Web Text))

Max Activating Token Index: 876