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

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

Neuron 3258 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2826. Min Act: -0.0001

Data Index: 566826 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2815. Min Act: -0.0001

Data Index: 1201226 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2240. Min Act: -0.0001

Data Index: 552933 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2398. Min Act: -0.0001

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2238. Min Act: -0.0001

Data Index: 104987 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1317152 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2204. Min Act: -0.0001

Data Index: 885487 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1164534 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1949. Min Act: -0.0001

Data Index: 971172 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1005330 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1814. Min Act: -0.0001

Data Index: 142252 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1738. Min Act: -0.0001

Data Index: 165668 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1065915 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1815. Min Act: -0.0001

Data Index: 190124 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1806. Min Act: -0.0001

Data Index: 552292 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1322926 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1906. Min Act: -0.0001

Data Index: 551646 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1546. Min Act: -0.0001

Data Index: 396359 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1203119 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1745. Min Act: -0.0001

Data Index: 982353 (C4 (Web Text))

Max Activating Token Index: 39