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

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

Neuron 3191 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: 0.1017. Min Range: -0.1017

Max Act: 0.1000. Min Act: -0.0000

Data Index: 243682 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.1017. Min Act: -0.0000

Data Index: 932719 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0909. Min Act: -0.0000

Data Index: 644500 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0844. Min Act: -0.0000

Data Index: 724729 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0848. Min Act: -0.0000

Data Index: 198202 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0812. Min Act: -0.0000

Data Index: 680046 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1281303 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0803. Min Act: -0.0000

Data Index: 543149 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1026473 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0791. Min Act: -0.0000

Data Index: 46762 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1325278 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0795. Min Act: -0.0000

Data Index: 321807 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1052364 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0742. Min Act: -0.0000

Data Index: 509767 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0810. Min Act: -0.0000

Data Index: 478265 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0783. Min Act: -0.0000

Data Index: 15006 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0757. Min Act: -0.0000

Data Index: 775826 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1216697 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0711. Min Act: -0.0000

Data Index: 607404 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0710. Min Act: -0.0000

Data Index: 702572 (C4 (Web Text))

Max Activating Token Index: 954