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

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

Neuron 2874 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: 0.0886. Min Range: -0.0886

Max Act: 0.0829. Min Act: -0.0001

Data Index: 257252 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1416404 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0750. Min Act: -0.0001

Data Index: 88468 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0765. Min Act: -0.0001

Data Index: 199124 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0642. Min Act: -0.0001

Data Index: 674927 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1510445 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1454731 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1245882 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1203484 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0642. Min Act: -0.0001

Data Index: 954588 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1153881 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0611. Min Act: -0.0001

Data Index: 548523 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0636. Min Act: -0.0001

Data Index: 80634 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0610. Min Act: -0.0001

Data Index: 662504 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1313454 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1004577 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1470604 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1008877 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0589. Min Act: -0.0001

Data Index: 450818 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 55