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

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

Neuron 5228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2218. Min Act: -0.0001

Data Index: 905367 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2252. Min Act: -0.0001

Data Index: 586572 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1961. Min Act: -0.0001

Data Index: 60115 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1928. Min Act: -0.0001

Data Index: 157650 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1972. Min Act: -0.0001

Data Index: 391008 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1908. Min Act: -0.0001

Data Index: 70929 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1019270 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1932. Min Act: -0.0001

Data Index: 641784 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1853. Min Act: -0.0001

Data Index: 161538 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1730. Min Act: -0.0001

Data Index: 346668 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1802. Min Act: -0.0001

Data Index: 270385 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1736. Min Act: -0.0001

Data Index: 254619 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1843. Min Act: -0.0001

Data Index: 339818 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1676. Min Act: -0.0001

Data Index: 316611 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1721. Min Act: -0.0001

Data Index: 793883 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1193394 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1148141 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1817. Min Act: -0.0001

Data Index: 878402 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1148988 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1090412 (C4 (Web Text))

Max Activating Token Index: 234