Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1931 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1261106 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2727. Min Act: -0.0000

Data Index: 670532 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2371. Min Act: -0.0001

Data Index: 1410120 (Python Code)

Max Activating Token Index: 447

Text #3

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2738. Min Act: -0.0001

Data Index: 826677 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2484. Min Act: -0.0001

Data Index: 1649299 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1577013 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1372117 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2119. Min Act: -0.0001

Data Index: 596847 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1450501 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1498647 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1524854 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2126. Min Act: -0.0001

Data Index: 689970 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1437843 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1379636 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2343. Min Act: -0.0001

Data Index: 1252459 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.1833. Min Act: -0.0000

Data Index: 106071 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1030339 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1560725 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.1875. Min Act: -0.0001

Data Index: 669897 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.1995. Min Act: -0.0001

Data Index: 1483130 (Python Code)

Max Activating Token Index: 710