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

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

Neuron 5239 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: 0.1026. Min Range: -0.1026

Max Act: 0.0812. Min Act: -0.0000

Data Index: 328205 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0880. Min Act: -0.0000

Data Index: 528974 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0000

Data Index: 584388 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0768. Min Act: -0.0000

Data Index: 573694 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1349203 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0807. Min Act: -0.0000

Data Index: 821712 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0882. Min Act: -0.0000

Data Index: 598193 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0797. Min Act: -0.0000

Data Index: 288549 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0748. Min Act: -0.0000

Data Index: 754966 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0793. Min Act: -0.0000

Data Index: 519446 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0809. Min Act: -0.0000

Data Index: 344044 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1273181 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0803. Min Act: -0.0001

Data Index: 896137 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0744. Min Act: -0.0000

Data Index: 360699 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0610. Min Act: -0.0000

Data Index: 954005 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0767. Min Act: -0.0000

Data Index: 138472 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0746. Min Act: -0.0000

Data Index: 253257 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1315955 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0750. Min Act: -0.0001

Data Index: 837528 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0765. Min Act: -0.0000

Data Index: 423265 (C4 (Web Text))

Max Activating Token Index: 350