Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2786 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1033269 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1505. Min Act: -0.0001

Data Index: 652903 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1492. Min Act: -0.0001

Data Index: 526394 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1212. Min Act: -0.0001

Data Index: 373282 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1247. Min Act: -0.0001

Data Index: 258780 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1074623 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1289. Min Act: -0.0001

Data Index: 625578 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1259089 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1243. Min Act: -0.0001

Data Index: 933424 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1139. Min Act: -0.0001

Data Index: 934226 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1033848 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1306. Min Act: -0.0001

Data Index: 180542 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1118. Min Act: -0.0001

Data Index: 896329 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1107. Min Act: -0.0002

Data Index: 522820 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1236. Min Act: -0.0001

Data Index: 478857 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1103. Min Act: -0.0001

Data Index: 176248 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1327430 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1115. Min Act: -0.0001

Data Index: 465595 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1156. Min Act: -0.0001

Data Index: 795096 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1113. Min Act: -0.0001

Data Index: 434096 (C4 (Web Text))

Max Activating Token Index: 13