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

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

Neuron 4954 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2257. Min Range: -5.2257

Max Act: 5.2257. Min Act: -0.0000

Data Index: 1485276 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 5.2257. Min Range: -5.2257

Max Act: 5.0426. Min Act: -0.0000

Data Index: 1544868 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 5.2257. Min Range: -5.2257

Max Act: 5.0021. Min Act: -0.0000

Data Index: 1421235 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.7577. Min Act: -0.0000

Data Index: 1392765 (Python Code)

Max Activating Token Index: 826

Text #4

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.7470. Min Act: -0.0000

Data Index: 1437126 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.4921. Min Act: -0.0000

Data Index: 1406281 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.8279. Min Act: -0.0000

Data Index: 1495989 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.6210. Min Act: -0.0000

Data Index: 1514285 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.5059. Min Act: -0.0000

Data Index: 1625645 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.4811. Min Act: -0.0000

Data Index: 1605236 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.4321. Min Act: -0.0000

Data Index: 1404793 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.2314. Min Act: -0.0000

Data Index: 1361686 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.1681. Min Act: -0.0000

Data Index: 1400719 (Python Code)

Max Activating Token Index: 530

Text #13

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.2941. Min Act: -0.0000

Data Index: 1536958 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.3589. Min Act: -0.0000

Data Index: 1577599 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.0033. Min Act: -0.0000

Data Index: 1399842 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.1766. Min Act: -0.0000

Data Index: 1405174 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 5.2257. Min Range: -5.2257

Max Act: 4.0098. Min Act: -0.0000

Data Index: 1503436 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 5.2257. Min Range: -5.2257

Max Act: 3.8204. Min Act: -0.0000

Data Index: 1518373 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 5.2257. Min Range: -5.2257

Max Act: 3.8348. Min Act: -0.0000

Data Index: 1408401 (Python Code)

Max Activating Token Index: 710