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

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

Neuron 1235 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: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0000

Data Index: 760721 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1226112 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1193. Min Act: -0.0000

Data Index: 542766 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1197. Min Act: -0.0000

Data Index: 8898 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1194. Min Act: -0.0000

Data Index: 516631 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1119. Min Act: -0.0000

Data Index: 561075 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1016. Min Act: -0.0000

Data Index: 42361 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1008. Min Act: -0.0000

Data Index: 617285 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1047. Min Act: -0.0000

Data Index: 439960 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0999. Min Act: -0.0000

Data Index: 271490 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0973. Min Act: -0.0000

Data Index: 907122 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0952. Min Act: -0.0000

Data Index: 198676 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0983. Min Act: -0.0000

Data Index: 717488 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0908. Min Act: 0.0000

Data Index: 1333401 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0936. Min Act: -0.0000

Data Index: 327060 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1157552 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0863. Min Act: -0.0000

Data Index: 679237 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1282996 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0846. Min Act: -0.0000

Data Index: 660178 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1322770 (C4 (Web Text))

Max Activating Token Index: 718