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

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

Neuron 4641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3207. Min Range: -2.3207

Max Act: 2.3207. Min Act: -0.0000

Data Index: 1390843 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 2.3207. Min Range: -2.3207

Max Act: 2.0357. Min Act: -0.0000

Data Index: 1652883 (Python Code)

Max Activating Token Index: 536

Text #2

Max Range: 2.3207. Min Range: -2.3207

Max Act: 2.0676. Min Act: -0.0000

Data Index: 1432200 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 2.3207. Min Range: -2.3207

Max Act: 2.0740. Min Act: -0.0000

Data Index: 1601756 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.9786. Min Act: -0.0000

Data Index: 1405955 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 2.3207. Min Range: -2.3207

Max Act: 2.1584. Min Act: -0.0000

Data Index: 1403008 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1423280 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.7751. Min Act: -0.0000

Data Index: 1372722 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1580591 (Python Code)

Max Activating Token Index: 344

Text #9

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1421965 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.8924. Min Act: -0.0000

Data Index: 1365034 (Python Code)

Max Activating Token Index: 852

Text #11

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1522599 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.7587. Min Act: -0.0000

Data Index: 1436956 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.8617. Min Act: -0.0000

Data Index: 1480562 (Python Code)

Max Activating Token Index: 217

Text #14

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.4430. Min Act: -0.0000

Data Index: 1420290 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1491155 (Python Code)

Max Activating Token Index: 328

Text #16

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1608177 (Python Code)

Max Activating Token Index: 156

Text #17

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1570879 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1459936 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1650184 (Python Code)

Max Activating Token Index: 176