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

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

Neuron 3256 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.5792. Min Act: -0.0000

Data Index: 850884 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.4378. Min Act: -0.0000

Data Index: 1337199 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.2571. Min Act: 0.0000

Data Index: 1534410 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.2226. Min Act: 0.0000

Data Index: 1619450 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1561668 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1650858 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1383247 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1466224 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1580636 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1535710 (Python Code)

Max Activating Token Index: 347

Text #10

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.1221. Min Act: 0.0000

Data Index: 1460875 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1414166 (Python Code)

Max Activating Token Index: 426

Text #12

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1383518 (Python Code)

Max Activating Token Index: 542

Text #13

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0357. Min Act: 0.0001

Data Index: 1538259 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1586247 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1315756 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1575645 (Python Code)

Max Activating Token Index: 631

Text #17

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0176. Min Act: 0.0000

Data Index: 1442860 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.0188. Min Act: 0.0000

Data Index: 1375070 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 1.5792. Min Range: -1.5792

Max Act: 1.1298. Min Act: -0.0000

Data Index: 517658 (C4 (Web Text))

Max Activating Token Index: 261