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

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

Neuron 1618 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: 0.1924. Min Range: -0.1924

Max Act: 0.1837. Min Act: -0.0002

Data Index: 337235 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1821. Min Act: -0.0002

Data Index: 716195 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1727. Min Act: -0.0002

Data Index: 180221 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1924. Min Act: -0.0002

Data Index: 1556996 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1701. Min Act: -0.0002

Data Index: 1275743 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1560. Min Act: -0.0002

Data Index: 1611625 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1643. Min Act: -0.0002

Data Index: 690865 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1721. Min Act: -0.0002

Data Index: 1638298 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1655227 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1501. Min Act: -0.0002

Data Index: 905777 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1477. Min Act: -0.0002

Data Index: 605484 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1434. Min Act: -0.0002

Data Index: 244208 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1406. Min Act: -0.0002

Data Index: 437581 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1396. Min Act: -0.0002

Data Index: 211599 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1433952 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1358. Min Act: -0.0002

Data Index: 204287 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1398. Min Act: -0.0002

Data Index: 1146412 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1491116 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1251. Min Act: -0.0002

Data Index: 241704 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1556187 (Python Code)

Max Activating Token Index: 95