Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2663. Min Act: -0.0000

Data Index: 276469 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2735. Min Act: -0.0001

Data Index: 725386 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2222. Min Act: -0.0000

Data Index: 954627 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1106497 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2184. Min Act: -0.0000

Data Index: 404182 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2166. Min Act: -0.0000

Data Index: 658957 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2088. Min Act: -0.0000

Data Index: 426424 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2087. Min Act: -0.0000

Data Index: 255137 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2078. Min Act: -0.0001

Data Index: 563897 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1296639 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2133. Min Act: -0.0001

Data Index: 702537 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1101268 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1034083 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2013. Min Act: -0.0000

Data Index: 231137 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1932. Min Act: -0.0000

Data Index: 173984 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1989. Min Act: -0.0000

Data Index: 977660 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1036337 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1954. Min Act: -0.0000

Data Index: 873697 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1894. Min Act: -0.0000

Data Index: 964542 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1959. Min Act: -0.0000

Data Index: 828255 (C4 (Web Text))

Max Activating Token Index: 487