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

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

Neuron 4721 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0002

Data Index: 584056 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0313. Min Act: -0.0002

Data Index: 670318 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1587222 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0278. Min Act: -0.0002

Data Index: 935155 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0286. Min Act: -0.0002

Data Index: 441720 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0277. Min Act: -0.0002

Data Index: 518594 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0274. Min Act: -0.0002

Data Index: 288006 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0263. Min Act: -0.0002

Data Index: 115135 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1422663 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1162281 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1416151 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0261. Min Act: -0.0002

Data Index: 106655 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0261. Min Act: -0.0002

Data Index: 100537 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1294050 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0262. Min Act: -0.0002

Data Index: 854772 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0253. Min Act: -0.0002

Data Index: 464063 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1603091 (Python Code)

Max Activating Token Index: 874

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0256. Min Act: -0.0002

Data Index: 691197 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0248. Min Act: -0.0002

Data Index: 385584 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1181921 (C4 (Web Text))

Max Activating Token Index: 100