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

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

Neuron 338 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: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0002

Data Index: 850226 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1272470 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1261. Min Act: -0.0002

Data Index: 929252 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1158934 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1223. Min Act: -0.0002

Data Index: 730873 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1242. Min Act: -0.0002

Data Index: 121012 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1253629 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1130057 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1220. Min Act: -0.0002

Data Index: 275256 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1340769 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1167. Min Act: -0.0002

Data Index: 394696 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1133. Min Act: -0.0002

Data Index: 893911 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1203. Min Act: -0.0002

Data Index: 994726 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1240. Min Act: -0.0002

Data Index: 565291 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1167. Min Act: -0.0002

Data Index: 885467 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1202. Min Act: -0.0002

Data Index: 800722 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1249. Min Act: -0.0002

Data Index: 642165 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1247. Min Act: -0.0002

Data Index: 840471 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1191. Min Act: -0.0002

Data Index: 629797 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1056634 (C4 (Web Text))

Max Activating Token Index: 854