Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5568 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0002

Data Index: 693749 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1433. Min Act: -0.0002

Data Index: 82716 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1349. Min Act: -0.0002

Data Index: 891129 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1322. Min Act: -0.0002

Data Index: 844473 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1330. Min Act: -0.0003

Data Index: 1019712 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1316. Min Act: -0.0002

Data Index: 120319 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1067424 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1034971 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1306. Min Act: -0.0002

Data Index: 455124 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1267. Min Act: -0.0003

Data Index: 241484 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1257. Min Act: -0.0002

Data Index: 525168 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1226. Min Act: -0.0003

Data Index: 567907 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1212. Min Act: -0.0002

Data Index: 604355 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1181. Min Act: -0.0002

Data Index: 625724 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1174710 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1176. Min Act: -0.0002

Data Index: 1121263 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1166. Min Act: -0.0002

Data Index: 912068 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1190. Min Act: -0.0002

Data Index: 955937 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1204. Min Act: -0.0002

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1196. Min Act: -0.0002

Data Index: 413816 (C4 (Web Text))

Max Activating Token Index: 69