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

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

Neuron 2947 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.9240. Min Act: -0.0000

Data Index: 1551338 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.8916. Min Act: -0.0000

Data Index: 1416104 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.9800. Min Act: -0.0000

Data Index: 1364685 (Python Code)

Max Activating Token Index: 987

Text #3

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.8315. Min Act: -0.0000

Data Index: 1623980 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 6.0298. Min Range: -6.0298

Max Act: 6.0298. Min Act: -0.0000

Data Index: 1408540 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.6718. Min Act: -0.0000

Data Index: 1394460 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.4490. Min Act: -0.0000

Data Index: 1429263 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.3985. Min Act: -0.0000

Data Index: 1437121 (Python Code)

Max Activating Token Index: 801

Text #8

Max Range: 6.0298. Min Range: -6.0298

Max Act: 4.9720. Min Act: -0.0000

Data Index: 1509345 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.6488. Min Act: -0.0000

Data Index: 1420060 (Python Code)

Max Activating Token Index: 931

Text #10

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.3265. Min Act: -0.0000

Data Index: 1447827 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.3164. Min Act: -0.0000

Data Index: 1634871 (Python Code)

Max Activating Token Index: 582

Text #12

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.1033. Min Act: -0.0000

Data Index: 1506436 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.6352. Min Act: -0.0000

Data Index: 1649435 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.2679. Min Act: -0.0000

Data Index: 1516712 (Python Code)

Max Activating Token Index: 926

Text #15

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.1014. Min Act: -0.0000

Data Index: 1389898 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.1209. Min Act: -0.0000

Data Index: 1510584 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.3375. Min Act: -0.0000

Data Index: 1401056 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.3419. Min Act: -0.0000

Data Index: 1450080 (Python Code)

Max Activating Token Index: 598

Text #19

Max Range: 6.0298. Min Range: -6.0298

Max Act: 5.3178. Min Act: -0.0000

Data Index: 1408762 (Python Code)

Max Activating Token Index: 415