Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1234. Min Act: -0.0003

Data Index: 476232 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0003

Data Index: 696446 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1224. Min Act: -0.0003

Data Index: 1185863 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1162. Min Act: -0.0003

Data Index: 161268 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1091. Min Act: -0.0003

Data Index: 516329 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1025. Min Act: -0.0003

Data Index: 925425 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1128. Min Act: -0.0003

Data Index: 616809 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1050. Min Act: -0.0003

Data Index: 533163 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1081. Min Act: -0.0003

Data Index: 596049 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1032. Min Act: -0.0003

Data Index: 77984 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1034. Min Act: -0.0003

Data Index: 954107 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1068. Min Act: -0.0003

Data Index: 900279 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1064. Min Act: -0.0003

Data Index: 53500 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1024. Min Act: -0.0003

Data Index: 30997 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1049. Min Act: -0.0003

Data Index: 129997 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1029. Min Act: -0.0003

Data Index: 1187499 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0997. Min Act: -0.0003

Data Index: 245201 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0968. Min Act: -0.0003

Data Index: 359172 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0997. Min Act: -0.0003

Data Index: 547735 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0947. Min Act: -0.0003

Data Index: 1321676 (C4 (Web Text))

Max Activating Token Index: 1015