Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1187 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1044882 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0714. Min Act: -0.0002

Data Index: 322858 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0649. Min Act: -0.0002

Data Index: 807986 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1252213 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1059781 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0596. Min Act: -0.0002

Data Index: 498699 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1173165 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0602. Min Act: -0.0002

Data Index: 383898 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0586. Min Act: -0.0002

Data Index: 32352 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0575. Min Act: -0.0002

Data Index: 138340 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1106639 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0570. Min Act: -0.0002

Data Index: 964865 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0569. Min Act: -0.0002

Data Index: 383858 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0536. Min Act: -0.0002

Data Index: 824922 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0570. Min Act: -0.0002

Data Index: 774649 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1149807 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0564. Min Act: -0.0001

Data Index: 244668 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0558. Min Act: -0.0001

Data Index: 542943 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0535. Min Act: -0.0002

Data Index: 835495 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0547. Min Act: -0.0001

Data Index: 200288 (C4 (Web Text))

Max Activating Token Index: 275