Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1820 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2413. Min Act: -0.0004

Data Index: 529697 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2426. Min Act: -0.0004

Data Index: 1251133 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2256. Min Act: -0.0004

Data Index: 1276332 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2141. Min Act: -0.0004

Data Index: 1318491 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2124. Min Act: -0.0004

Data Index: 247214 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2091. Min Act: -0.0004

Data Index: 1099485 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2042. Min Act: -0.0004

Data Index: 402266 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1630. Min Act: -0.0004

Data Index: 854661 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2062. Min Act: -0.0004

Data Index: 764170 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1973. Min Act: -0.0004

Data Index: 203600 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1827. Min Act: -0.0004

Data Index: 510262 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1934. Min Act: -0.0004

Data Index: 309192 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1991. Min Act: -0.0004

Data Index: 399191 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1849. Min Act: -0.0004

Data Index: 251333 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1846. Min Act: -0.0004

Data Index: 496383 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1838. Min Act: -0.0004

Data Index: 680523 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1842. Min Act: -0.0004

Data Index: 588351 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1973. Min Act: -0.0004

Data Index: 716336 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1961. Min Act: -0.0004

Data Index: 399652 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1868. Min Act: -0.0004

Data Index: 268867 (C4 (Web Text))

Max Activating Token Index: 478