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

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

Neuron 1486 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1720. Min Act: -0.0001

Data Index: 109327 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1491. Min Act: -0.0001

Data Index: 575205 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1073. Min Act: -0.0001

Data Index: 792412 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1219. Min Act: -0.0001

Data Index: 915653 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1201 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1061. Min Act: -0.0001

Data Index: 392927 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1096. Min Act: -0.0001

Data Index: 539060 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0754. Min Act: -0.0001

Data Index: 939071 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1311893 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1058. Min Act: -0.0001

Data Index: 37257 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1042. Min Act: -0.0001

Data Index: 477984 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1045. Min Act: -0.0001

Data Index: 946072 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1290200 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1116531 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0932. Min Act: -0.0001

Data Index: 432782 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0942. Min Act: -0.0001

Data Index: 800382 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1101. Min Act: -0.0001

Data Index: 381761 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1271658 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1185958 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1097. Min Act: -0.0001

Data Index: 683176 (C4 (Web Text))

Max Activating Token Index: 619