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

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

Neuron 883 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5852. Min Act: -0.0002

Data Index: 1280346 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.6045. Min Act: -0.0002

Data Index: 423126 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5492. Min Act: -0.0002

Data Index: 421944 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5748. Min Act: -0.0002

Data Index: 697212 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5282. Min Act: -0.0002

Data Index: 1265670 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5062. Min Act: -0.0002

Data Index: 1246144 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5109. Min Act: -0.0002

Data Index: 642596 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5804. Min Act: -0.0002

Data Index: 329572 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4914. Min Act: -0.0002

Data Index: 14863 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5352. Min Act: -0.0002

Data Index: 1245473 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5019. Min Act: -0.0002

Data Index: 960841 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4856. Min Act: -0.0002

Data Index: 619486 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4578. Min Act: -0.0001

Data Index: 891889 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5464. Min Act: -0.0001

Data Index: 946910 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4830. Min Act: -0.0002

Data Index: 184026 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5104. Min Act: -0.0002

Data Index: 493805 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5153. Min Act: -0.0002

Data Index: 946363 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5055. Min Act: -0.0001

Data Index: 794845 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5230. Min Act: -0.0002

Data Index: 1189554 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4574. Min Act: -0.0001

Data Index: 914807 (C4 (Web Text))

Max Activating Token Index: 536