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

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

Neuron 3548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1532. Min Act: -0.0000

Data Index: 433202 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1647. Min Act: -0.0000

Data Index: 666790 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1610. Min Act: -0.0000

Data Index: 396995 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1351. Min Act: -0.0000

Data Index: 619167 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1320. Min Act: -0.0000

Data Index: 792278 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1341209 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1288. Min Act: -0.0000

Data Index: 49332 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1251. Min Act: -0.0000

Data Index: 739923 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1256. Min Act: -0.0000

Data Index: 569951 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1294. Min Act: -0.0000

Data Index: 338746 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1217. Min Act: -0.0000

Data Index: 319198 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1203. Min Act: -0.0000

Data Index: 503539 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1158. Min Act: -0.0000

Data Index: 240407 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1225. Min Act: -0.0000

Data Index: 142003 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1180. Min Act: -0.0000

Data Index: 679910 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1132. Min Act: -0.0000

Data Index: 513884 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1150885 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1140. Min Act: -0.0000

Data Index: 551450 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1158. Min Act: -0.0000

Data Index: 747730 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1239. Min Act: -0.0000

Data Index: 992867 (C4 (Web Text))

Max Activating Token Index: 919