Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 729 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1241173 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2479. Min Act: -0.0001

Data Index: 243016 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2187. Min Act: -0.0001

Data Index: 888886 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2028. Min Act: -0.0000

Data Index: 57126 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2089. Min Act: -0.0001

Data Index: 859378 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2027. Min Act: -0.0001

Data Index: 169270 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1990. Min Act: -0.0001

Data Index: 39566 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1931. Min Act: -0.0001

Data Index: 212995 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1959. Min Act: -0.0001

Data Index: 368937 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1155688 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1843. Min Act: -0.0001

Data Index: 67198 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1896. Min Act: -0.0001

Data Index: 233556 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1815. Min Act: -0.0001

Data Index: 259335 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1845. Min Act: -0.0001

Data Index: 760657 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1810. Min Act: -0.0001

Data Index: 878191 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1814. Min Act: -0.0001

Data Index: 713200 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1873. Min Act: -0.0001

Data Index: 866097 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1831. Min Act: -0.0001

Data Index: 64263 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1196266 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1684. Min Act: -0.0001

Data Index: 677939 (C4 (Web Text))

Max Activating Token Index: 349