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

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

Neuron 2500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.7971. Min Act: -0.0000

Data Index: 840003 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.6151. Min Act: -0.0000

Data Index: 855515 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.5018. Min Act: -0.0000

Data Index: 443140 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.5661. Min Act: -0.0000

Data Index: 1203149 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.6043. Min Act: -0.0000

Data Index: 287906 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.4710. Min Act: -0.0000

Data Index: 1174362 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.5909. Min Act: -0.0000

Data Index: 480208 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.5538. Min Act: -0.0000

Data Index: 456742 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.4098. Min Act: -0.0000

Data Index: 1004895 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.3984. Min Act: -0.0000

Data Index: 259775 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.3725. Min Act: -0.0000

Data Index: 111989 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.2521. Min Act: -0.0000

Data Index: 879535 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.2065. Min Act: -0.0000

Data Index: 780864 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 2.7971. Min Range: -2.7971

Max Act: 1.9660. Min Act: -0.0000

Data Index: 784659 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.1930. Min Act: -0.0000

Data Index: 1155835 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.1736. Min Act: -0.0000

Data Index: 1038812 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.1247. Min Act: -0.0000

Data Index: 482105 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.2359. Min Act: -0.0000

Data Index: 944125 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.0805. Min Act: -0.0000

Data Index: 592898 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 2.7971. Min Range: -2.7971

Max Act: 2.1899. Min Act: -0.0000

Data Index: 575163 (C4 (Web Text))

Max Activating Token Index: 71