Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2845 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0968. Min Act: -0.0000

Data Index: 731572 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0865. Min Act: -0.0000

Data Index: 340346 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0845. Min Act: -0.0000

Data Index: 893497 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0875. Min Act: -0.0000

Data Index: 961700 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0782. Min Act: -0.0000

Data Index: 295546 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0769. Min Act: -0.0000

Data Index: 851691 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0844. Min Act: -0.0000

Data Index: 944661 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0730. Min Act: -0.0000

Data Index: 537270 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1323287 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1168851 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0744. Min Act: -0.0000

Data Index: 253793 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0712. Min Act: -0.0000

Data Index: 724226 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0732. Min Act: -0.0000

Data Index: 478755 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1007362 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0683. Min Act: -0.0000

Data Index: 130021 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0734. Min Act: -0.0000

Data Index: 23571 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1136950 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0636. Min Act: -0.0000

Data Index: 633857 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0660. Min Act: -0.0000

Data Index: 389922 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0696. Min Act: -0.0000

Data Index: 340349 (C4 (Web Text))

Max Activating Token Index: 306