Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1203 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0003

Data Index: 610593 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1111294 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1157844 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0268. Min Act: -0.0003

Data Index: 130702 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0249. Min Act: -0.0004

Data Index: 1357501 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1595501 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0250. Min Act: -0.0003

Data Index: 685230 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0246. Min Act: -0.0003

Data Index: 835372 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0235. Min Act: -0.0003

Data Index: 108060 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0003

Data Index: 984597 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0003

Data Index: 212969 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1568618 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1240747 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1500352 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1292204 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1336181 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0219. Min Act: -0.0003

Data Index: 62576 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0216. Min Act: -0.0003

Data Index: 10605 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0003

Data Index: 261928 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0222. Min Act: -0.0003

Data Index: 488534 (C4 (Web Text))

Max Activating Token Index: 637