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

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

Neuron 4615 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1157. Min Act: -0.0000

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1222. Min Act: -0.0000

Data Index: 746079 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1198. Min Act: -0.0000

Data Index: 114677 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1187. Min Act: -0.0000

Data Index: 505017 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1035. Min Act: -0.0000

Data Index: 722629 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1002869 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1146904 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1099720 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0946. Min Act: -0.0000

Data Index: 572306 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0946. Min Act: -0.0000

Data Index: 499306 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0987. Min Act: -0.0000

Data Index: 175759 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1006. Min Act: -0.0000

Data Index: 952218 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0939. Min Act: -0.0000

Data Index: 238770 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1006. Min Act: -0.0000

Data Index: 742235 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1204727 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0878. Min Act: -0.0000

Data Index: 737635 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0896. Min Act: -0.0000

Data Index: 109493 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1105272 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1178795 (C4 (Web Text))

Max Activating Token Index: 388