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

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

Neuron 3355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1305370 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1490154 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0266. Min Act: -0.0002

Data Index: 16435 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0002

Data Index: 693224 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0264. Min Act: -0.0001

Data Index: 599534 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1273339 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0002

Data Index: 683357 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0002

Data Index: 860727 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1479345 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1528779 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1548955 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1421907 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0249. Min Act: -0.0002

Data Index: 517359 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0248. Min Act: -0.0002

Data Index: 872550 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0249. Min Act: -0.0002

Data Index: 332925 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1541747 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1429789 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0246. Min Act: -0.0002

Data Index: 2356 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0241. Min Act: -0.0002

Data Index: 28863 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1419579 (Python Code)

Max Activating Token Index: 178