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

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

Neuron 751 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7280. Min Act: -0.0003

Data Index: 610186 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7497. Min Act: -0.0003

Data Index: 146957 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6741. Min Act: -0.0002

Data Index: 1293235 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7210. Min Act: -0.0002

Data Index: 531062 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6714. Min Act: -0.0003

Data Index: 984681 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7330. Min Act: -0.0003

Data Index: 337433 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7274. Min Act: -0.0003

Data Index: 156887 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6755. Min Act: -0.0003

Data Index: 1342246 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7896. Min Act: -0.0003

Data Index: 539649 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6620. Min Act: -0.0003

Data Index: 629668 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6857. Min Act: -0.0003

Data Index: 1019886 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6217. Min Act: -0.0003

Data Index: 573066 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6630. Min Act: -0.0003

Data Index: 552071 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6887. Min Act: -0.0003

Data Index: 146891 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6612. Min Act: -0.0003

Data Index: 92073 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6385. Min Act: -0.0003

Data Index: 223877 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5545. Min Act: -0.0003

Data Index: 295950 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6262. Min Act: -0.0003

Data Index: 667783 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6271. Min Act: -0.0003

Data Index: 660638 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6886. Min Act: -0.0003

Data Index: 706221 (C4 (Web Text))

Max Activating Token Index: 235