Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3163 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4632. Min Act: -0.0001

Data Index: 828099 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4439. Min Act: -0.0001

Data Index: 205219 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4231. Min Act: -0.0001

Data Index: 305426 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4080. Min Act: -0.0001

Data Index: 426500 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1333381 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1354531 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4031. Min Act: -0.0001

Data Index: 861828 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1355420 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4007. Min Act: -0.0001

Data Index: 1224443 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3973. Min Act: -0.0001

Data Index: 553792 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3814. Min Act: -0.0001

Data Index: 377264 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3954. Min Act: -0.0001

Data Index: 886479 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3859. Min Act: -0.0001

Data Index: 480293 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1246858 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1337882 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3837. Min Act: -0.0001

Data Index: 782479 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3679. Min Act: -0.0001

Data Index: 889853 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3647. Min Act: -0.0001

Data Index: 806417 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3756. Min Act: -0.0001

Data Index: 225932 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1094528 (C4 (Web Text))

Max Activating Token Index: 75