Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0003

Data Index: 452782 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1359. Min Act: -0.0003

Data Index: 906907 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1326. Min Act: -0.0003

Data Index: 1111556 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1274. Min Act: -0.0003

Data Index: 875286 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1262. Min Act: -0.0003

Data Index: 74132 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1266. Min Act: -0.0003

Data Index: 526421 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1248. Min Act: -0.0003

Data Index: 440330 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1233. Min Act: -0.0003

Data Index: 473798 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1213. Min Act: -0.0003

Data Index: 1153245 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1201. Min Act: -0.0003

Data Index: 1274199 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1236. Min Act: -0.0003

Data Index: 35163 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1180. Min Act: -0.0003

Data Index: 649651 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1170. Min Act: -0.0003

Data Index: 309770 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1156. Min Act: -0.0003

Data Index: 526426 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1174. Min Act: -0.0003

Data Index: 995127 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1185. Min Act: -0.0003

Data Index: 1298266 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1137. Min Act: -0.0003

Data Index: 953585 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1112. Min Act: -0.0003

Data Index: 569954 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1142. Min Act: -0.0003

Data Index: 303482 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1167. Min Act: -0.0003

Data Index: 1114112 (C4 (Web Text))

Max Activating Token Index: 309