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

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

Neuron 3471 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: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0001

Data Index: 287905 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0928. Min Act: -0.0001

Data Index: 256630 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0779. Min Act: -0.0001

Data Index: 798223 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0807. Min Act: -0.0001

Data Index: 496050 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1164872 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0798. Min Act: -0.0001

Data Index: 232419 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1153581 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0735. Min Act: -0.0001

Data Index: 906 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0679. Min Act: -0.0001

Data Index: 16267 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0752. Min Act: -0.0001

Data Index: 78523 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0741. Min Act: -0.0001

Data Index: 923111 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1329544 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0667. Min Act: -0.0001

Data Index: 103341 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0671. Min Act: -0.0001

Data Index: 908180 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0650. Min Act: -0.0001

Data Index: 410329 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0723. Min Act: -0.0001

Data Index: 870989 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0644. Min Act: -0.0001

Data Index: 874520 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0615. Min Act: -0.0001

Data Index: 71021 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0639. Min Act: -0.0001

Data Index: 345142 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0650. Min Act: -0.0001

Data Index: 655556 (C4 (Web Text))

Max Activating Token Index: 782