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

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

Neuron 1255 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: 0.2228. Min Range: -0.2228

Max Act: 0.2228. Min Act: -0.0002

Data Index: 1021440 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2169. Min Act: -0.0002

Data Index: 180797 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1947. Min Act: -0.0002

Data Index: 280986 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1957. Min Act: -0.0002

Data Index: 705477 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2016. Min Act: -0.0002

Data Index: 407653 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1928. Min Act: -0.0002

Data Index: 238058 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1906. Min Act: -0.0002

Data Index: 113471 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1905. Min Act: -0.0002

Data Index: 789983 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1842. Min Act: -0.0002

Data Index: 696563 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1884. Min Act: -0.0002

Data Index: 1019989 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1696. Min Act: -0.0002

Data Index: 1118538 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2046. Min Act: -0.0002

Data Index: 969863 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1774. Min Act: -0.0002

Data Index: 585054 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1756. Min Act: -0.0002

Data Index: 507293 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1727. Min Act: -0.0002

Data Index: 795206 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1735. Min Act: -0.0002

Data Index: 1193710 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1724. Min Act: -0.0002

Data Index: 166321 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1680. Min Act: -0.0002

Data Index: 915407 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1631. Min Act: -0.0002

Data Index: 650814 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1887. Min Act: -0.0002

Data Index: 1332684 (C4 (Web Text))

Max Activating Token Index: 180