Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4000 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0001

Data Index: 103929 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0308. Min Act: -0.0001

Data Index: 531270 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1439752 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1487108 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0313. Min Act: -0.0001

Data Index: 993044 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1519654 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1602447 (Python Code)

Max Activating Token Index: 403

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1592504 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0268. Min Act: -0.0001

Data Index: 624185 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1391771 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0275. Min Act: -0.0001

Data Index: 35986 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1516880 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1049923 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1568101 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1012993 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1458324 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1568080 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0190. Min Act: -0.0001

Data Index: 704873 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1378958 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1480517 (Python Code)

Max Activating Token Index: 740