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

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

Neuron 647 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0003

Data Index: 730736 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0695. Min Act: -0.0003

Data Index: 713155 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0662. Min Act: -0.0003

Data Index: 977633 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0671. Min Act: -0.0004

Data Index: 1298241 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0680. Min Act: -0.0003

Data Index: 162596 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1543469 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1076734 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0608. Min Act: -0.0003

Data Index: 621709 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0639. Min Act: -0.0003

Data Index: 872317 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0650. Min Act: -0.0003

Data Index: 270449 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0638. Min Act: -0.0003

Data Index: 738708 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0653. Min Act: -0.0003

Data Index: 541134 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0637. Min Act: -0.0003

Data Index: 617136 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0591. Min Act: -0.0003

Data Index: 259503 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0611. Min Act: -0.0003

Data Index: 844908 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0565. Min Act: -0.0003

Data Index: 300171 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0674. Min Act: -0.0003

Data Index: 876777 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1082738 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0529. Min Act: -0.0003

Data Index: 661185 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0565. Min Act: -0.0003

Data Index: 592989 (C4 (Web Text))

Max Activating Token Index: 64