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

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

Neuron 1884 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1441462 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1634836 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1392819 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1379738 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2416. Min Act: -0.0001

Data Index: 1617356 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2485. Min Act: -0.0001

Data Index: 1544125 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1644662 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1482012 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2387. Min Act: -0.0001

Data Index: 1625656 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1538300 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2374. Min Act: -0.0001

Data Index: 1383302 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1459337 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1383529 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2337. Min Act: -0.0001

Data Index: 1351236 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1410204 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1588810 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2317. Min Act: -0.0001

Data Index: 1432944 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1390928 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1418226 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1620731 (Python Code)

Max Activating Token Index: 16