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

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

Neuron 3234 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5695. Min Act: -0.0002

Data Index: 607445 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4996. Min Act: -0.0002

Data Index: 432464 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.2585. Min Act: -0.0002

Data Index: 1589427 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1895. Min Act: -0.0002

Data Index: 533053 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1393293 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1442227 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1366. Min Act: -0.0002

Data Index: 1373266 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1282. Min Act: -0.0002

Data Index: 1592016 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1635726 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1466117 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1264. Min Act: -0.0002

Data Index: 1442768 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1485235 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1497217 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1577820 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1468170 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1405996 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1210. Min Act: -0.0002

Data Index: 1373461 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1427224 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1577973 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.1193. Min Act: -0.0002

Data Index: 1363379 (Python Code)

Max Activating Token Index: 4