Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 644 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1639879 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1379493 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1557737 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1585100 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1505343 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1362243 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1387089 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1574305 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1505201 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1403923 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1603597 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1437546 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1588813 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1641920 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1529184 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1597721 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1612875 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1480109 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1547984 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1434176 (Python Code)

Max Activating Token Index: 3