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

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

Neuron 3305 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1050711 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0690. Min Act: -0.0002

Data Index: 585075 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0666. Min Act: -0.0002

Data Index: 25174 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1617736 (Python Code)

Max Activating Token Index: 199

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0581. Min Act: -0.0002

Data Index: 723297 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0492. Min Act: -0.0002

Data Index: 742468 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1451190 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1547971 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1471629 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0578. Min Act: -0.0002

Data Index: 422092 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0552. Min Act: -0.0002

Data Index: 2671 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1314948 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0480. Min Act: -0.0002

Data Index: 414845 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0518. Min Act: -0.0002

Data Index: 685981 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0513. Min Act: -0.0003

Data Index: 366011 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0516. Min Act: -0.0002

Data Index: 28713 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1593992 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1644590 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0531. Min Act: -0.0002

Data Index: 160543 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0490. Min Act: -0.0002

Data Index: 108456 (C4 (Web Text))

Max Activating Token Index: 751