Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1376 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1569. Min Act: -0.0002

Data Index: 120382 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1448. Min Act: -0.0002

Data Index: 429723 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1455. Min Act: -0.0002

Data Index: 712084 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1387. Min Act: -0.0002

Data Index: 775815 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1392. Min Act: -0.0002

Data Index: 111404 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1370. Min Act: -0.0002

Data Index: 845465 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1382. Min Act: -0.0002

Data Index: 788095 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1373. Min Act: -0.0002

Data Index: 1093664 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1342446 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1413. Min Act: -0.0002

Data Index: 1160114 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1130910 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1284. Min Act: -0.0002

Data Index: 229908 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1262. Min Act: -0.0002

Data Index: 704658 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1284. Min Act: -0.0002

Data Index: 70551 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1176114 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1274. Min Act: -0.0002

Data Index: 69257 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1268. Min Act: -0.0002

Data Index: 213589 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1226. Min Act: -0.0002

Data Index: 758795 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1258. Min Act: -0.0002

Data Index: 431257 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1270. Min Act: -0.0002

Data Index: 807630 (C4 (Web Text))

Max Activating Token Index: 698