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

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

Neuron 3300 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1765. Min Act: -0.0001

Data Index: 473323 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1428. Min Act: -0.0001

Data Index: 430556 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1901. Min Act: -0.0001

Data Index: 621192 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1389. Min Act: -0.0001

Data Index: 855923 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1357. Min Act: -0.0001

Data Index: 1178475 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0999. Min Act: -0.0001

Data Index: 369976 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1283. Min Act: -0.0001

Data Index: 489594 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1290. Min Act: -0.0001

Data Index: 1138979 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1264. Min Act: -0.0001

Data Index: 165258 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1237. Min Act: -0.0001

Data Index: 1315829 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0931. Min Act: -0.0001

Data Index: 433852 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0857. Min Act: -0.0001

Data Index: 951316 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0779. Min Act: -0.0001

Data Index: 378947 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1085. Min Act: -0.0001

Data Index: 698729 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0715. Min Act: -0.0001

Data Index: 1159839 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1025. Min Act: -0.0001

Data Index: 981866 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0969. Min Act: -0.0001

Data Index: 407951 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0627. Min Act: -0.0001

Data Index: 90288 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.0932. Min Act: -0.0001

Data Index: 412168 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.1901. Min Range: -1.1901

Max Act: 1.1222. Min Act: -0.0001

Data Index: 359616 (C4 (Web Text))

Max Activating Token Index: 825