Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1328824 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0579. Min Act: -0.0003

Data Index: 573130 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0589. Min Act: -0.0003

Data Index: 903861 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0586. Min Act: -0.0003

Data Index: 671919 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0585. Min Act: -0.0003

Data Index: 469777 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0568. Min Act: -0.0003

Data Index: 217354 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1212409 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0561. Min Act: -0.0004

Data Index: 1316697 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1227101 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1281300 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0562. Min Act: -0.0002

Data Index: 20080 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1196921 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1099063 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0537. Min Act: -0.0004

Data Index: 37728 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1347264 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0558. Min Act: -0.0002

Data Index: 412190 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0556. Min Act: -0.0003

Data Index: 564891 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0573. Min Act: -0.0003

Data Index: 268571 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1063620 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1323756 (C4 (Web Text))

Max Activating Token Index: 781