Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1086 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1394976 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1422018 (Python Code)

Max Activating Token Index: 657

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1600808 (Python Code)

Max Activating Token Index: 722

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1633970 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1552067 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0241. Min Act: -0.0001

Data Index: 510093 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1523416 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1501581 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1578714 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1566760 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1539338 (Python Code)

Max Activating Token Index: 639

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1506674 (Python Code)

Max Activating Token Index: 859

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1225307 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1366549 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1560836 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0220. Min Act: -0.0001

Data Index: 330252 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1555743 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1564256 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1458023 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0228. Min Act: -0.0001

Data Index: 1549710 (Python Code)

Max Activating Token Index: 976