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

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

Neuron 2005 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2709. Min Act: -0.0001

Data Index: 101166 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2363. Min Act: -0.0001

Data Index: 1329743 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2156. Min Act: -0.0001

Data Index: 296134 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1730. Min Act: -0.0000

Data Index: 908967 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1865. Min Act: -0.0000

Data Index: 850048 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1128763 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1286538 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1776. Min Act: -0.0000

Data Index: 984514 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1215959 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1694. Min Act: -0.0000

Data Index: 460543 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1739. Min Act: -0.0001

Data Index: 286400 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1481. Min Act: -0.0000

Data Index: 721453 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1255740 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1205670 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1223945 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1627. Min Act: -0.0000

Data Index: 472107 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1049527 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1192971 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1238699 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1450. Min Act: -0.0001

Data Index: 544031 (C4 (Web Text))

Max Activating Token Index: 569