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

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

Neuron 314 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0003

Data Index: 349296 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1048158 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1219245 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1169076 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0242. Min Act: -0.0002

Data Index: 42029 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0221. Min Act: -0.0003

Data Index: 7749 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0219. Min Act: -0.0003

Data Index: 529425 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0202. Min Act: -0.0002

Data Index: 424789 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0205. Min Act: -0.0003

Data Index: 143318 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0203. Min Act: -0.0002

Data Index: 213356 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0211. Min Act: -0.0002

Data Index: 600561 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0201. Min Act: -0.0003

Data Index: 920983 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0204. Min Act: -0.0003

Data Index: 951844 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0202. Min Act: -0.0003

Data Index: 106719 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1217186 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0188. Min Act: -0.0003

Data Index: 551331 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0189. Min Act: -0.0003

Data Index: 937556 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1094578 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1288403 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0184. Min Act: -0.0003

Data Index: 232754 (C4 (Web Text))

Max Activating Token Index: 977