Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2216. Min Act: -0.0003

Data Index: 316130 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2178. Min Act: -0.0003

Data Index: 139553 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2005. Min Act: -0.0003

Data Index: 797280 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2032. Min Act: -0.0003

Data Index: 424121 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1975. Min Act: -0.0003

Data Index: 966220 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1939. Min Act: -0.0003

Data Index: 4442 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1964. Min Act: -0.0003

Data Index: 1247206 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1850. Min Act: -0.0003

Data Index: 1049441 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1825. Min Act: -0.0003

Data Index: 811898 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1812. Min Act: -0.0003

Data Index: 864209 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1820. Min Act: -0.0003

Data Index: 470494 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1801. Min Act: -0.0003

Data Index: 811023 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1850. Min Act: -0.0003

Data Index: 235079 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1821. Min Act: -0.0003

Data Index: 1137519 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1801. Min Act: -0.0003

Data Index: 624948 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1850. Min Act: -0.0003

Data Index: 542765 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1771. Min Act: -0.0003

Data Index: 1097002 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1831. Min Act: -0.0004

Data Index: 173065 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1770. Min Act: -0.0003

Data Index: 957983 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1704. Min Act: -0.0003

Data Index: 155362 (C4 (Web Text))

Max Activating Token Index: 787