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

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

Neuron 3030 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0002

Data Index: 220129 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0999. Min Act: -0.0002

Data Index: 599442 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1006. Min Act: -0.0002

Data Index: 69427 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1064. Min Act: -0.0002

Data Index: 622502 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0871. Min Act: -0.0002

Data Index: 849488 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1156310 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1012. Min Act: -0.0002

Data Index: 980314 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1062120 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0958. Min Act: -0.0002

Data Index: 391825 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0923. Min Act: -0.0002

Data Index: 218943 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0855. Min Act: -0.0002

Data Index: 852957 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1230990 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0835. Min Act: -0.0002

Data Index: 476792 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1011735 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0854. Min Act: -0.0002

Data Index: 774376 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0943. Min Act: -0.0002

Data Index: 180390 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0875. Min Act: -0.0002

Data Index: 650071 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1140998 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0857. Min Act: -0.0002

Data Index: 152690 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1322848 (C4 (Web Text))

Max Activating Token Index: 434