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

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

Neuron 4416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0001

Data Index: 755072 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0000

Data Index: 1628362 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1548968 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0263. Min Act: -0.0000

Data Index: 1599882 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1048249 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1001962 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0266. Min Act: -0.0001

Data Index: 346511 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0001

Data Index: 490628 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1234831 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1446926 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0234. Min Act: -0.0001

Data Index: 987979 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0000

Data Index: 1604696 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0254. Min Act: -0.0000

Data Index: 76787 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1570717 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0001

Data Index: 646537 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0246. Min Act: -0.0000

Data Index: 1547792 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0242. Min Act: -0.0001

Data Index: 365871 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0213. Min Act: -0.0001

Data Index: 566776 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0219. Min Act: -0.0000

Data Index: 1647612 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1415660 (Python Code)

Max Activating Token Index: 928