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

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

Neuron 1972 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1365034 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.2281. Min Act: -0.0000

Data Index: 1606306 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1580495 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1333608 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1156124 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1473396 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1652883 (Python Code)

Max Activating Token Index: 588

Text #7

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1522599 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1403008 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1580591 (Python Code)

Max Activating Token Index: 396

Text #10

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1405955 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1372722 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1390843 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1388387 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9510. Min Act: -0.0000

Data Index: 219313 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1558507 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1488383 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1432200 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1529334 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9748. Min Act: -0.0000

Data Index: 641693 (C4 (Web Text))

Max Activating Token Index: 553