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

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

Neuron 1380 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1621. Min Act: -0.0002

Data Index: 781922 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1136460 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1412. Min Act: -0.0002

Data Index: 454233 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1323. Min Act: -0.0002

Data Index: 679051 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1282260 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1260088 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1040278 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1210. Min Act: -0.0002

Data Index: 531075 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1281. Min Act: -0.0002

Data Index: 1169613 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1261. Min Act: -0.0002

Data Index: 445590 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1254. Min Act: -0.0002

Data Index: 966682 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1189. Min Act: -0.0002

Data Index: 252079 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1224. Min Act: -0.0002

Data Index: 911171 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1081511 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1134. Min Act: -0.0002

Data Index: 38786 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1267. Min Act: -0.0002

Data Index: 814878 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1109. Min Act: -0.0002

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1217. Min Act: -0.0002

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1075. Min Act: -0.0002

Data Index: 756640 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.1621. Min Range: -0.1621

Max Act: 0.1252. Min Act: -0.0002

Data Index: 234843 (C4 (Web Text))

Max Activating Token Index: 714