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

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

Neuron 3626 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3565. Min Range: -1.3565

Max Act: 1.3565. Min Act: -0.0000

Data Index: 945129 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.3565. Min Range: -1.3565

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1054903 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1061785 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.9213. Min Act: -0.0000

Data Index: 699464 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1291054 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.9274. Min Act: -0.0000

Data Index: 936125 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.9814. Min Act: -0.0000

Data Index: 674065 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1130166 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7344. Min Act: -0.0000

Data Index: 921279 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1328273 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7791. Min Act: -0.0000

Data Index: 807445 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.6792. Min Act: -0.0000

Data Index: 153273 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1086554 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7448. Min Act: -0.0000

Data Index: 678473 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7155. Min Act: -0.0000

Data Index: 293796 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7445. Min Act: -0.0000

Data Index: 335677 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8054. Min Act: -0.0000

Data Index: 139492 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.6886. Min Act: -0.0000

Data Index: 849981 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1254660 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.6192. Min Act: -0.0000

Data Index: 155443 (C4 (Web Text))

Max Activating Token Index: 504