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

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

Neuron 692 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: 0.1613. Min Range: -0.1613

Max Act: 0.1613. Min Act: -0.0002

Data Index: 224270 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1237. Min Act: -0.0002

Data Index: 614178 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1102. Min Act: -0.0002

Data Index: 469289 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1329747 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1196570 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1105. Min Act: -0.0002

Data Index: 447255 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1143. Min Act: -0.0002

Data Index: 442120 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1296379 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1105. Min Act: -0.0002

Data Index: 646211 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1054. Min Act: -0.0002

Data Index: 570349 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1287144 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0898. Min Act: -0.0002

Data Index: 153550 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1035. Min Act: -0.0002

Data Index: 540796 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1150. Min Act: -0.0002

Data Index: 271636 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0840. Min Act: -0.0002

Data Index: 893003 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1029. Min Act: -0.0002

Data Index: 767152 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1153. Min Act: -0.0002

Data Index: 464566 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0884. Min Act: -0.0002

Data Index: 190725 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1196561 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1163300 (C4 (Web Text))

Max Activating Token Index: 728