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

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

Neuron 2596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0001

Data Index: 27460 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1232586 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1019401 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0972. Min Act: -0.0001

Data Index: 390779 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0934. Min Act: -0.0001

Data Index: 439011 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0930. Min Act: -0.0000

Data Index: 695543 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0911. Min Act: -0.0001

Data Index: 632597 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0909. Min Act: -0.0001

Data Index: 836043 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0877. Min Act: -0.0001

Data Index: 112026 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1099667 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1092956 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0857. Min Act: -0.0001

Data Index: 400991 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0829. Min Act: -0.0001

Data Index: 315903 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0793. Min Act: -0.0001

Data Index: 751480 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0854. Min Act: -0.0001

Data Index: 562810 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0840. Min Act: -0.0001

Data Index: 816032 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0870. Min Act: -0.0001

Data Index: 363998 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1279312 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1122166 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0821. Min Act: -0.0001

Data Index: 913807 (C4 (Web Text))

Max Activating Token Index: 111