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

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

Neuron 1825 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: 0.1115. Min Range: -0.1115

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1451006 (Python Code)

Max Activating Token Index: 451

Text #1

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1115. Min Act: -0.0000

Data Index: 264574 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0979. Min Act: -0.0000

Data Index: 746494 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0926. Min Act: -0.0000

Data Index: 878720 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0896. Min Act: -0.0000

Data Index: 667760 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1245768 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0891. Min Act: -0.0000

Data Index: 817760 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0761. Min Act: -0.0000

Data Index: 841650 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0811. Min Act: -0.0000

Data Index: 608261 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0811. Min Act: -0.0000

Data Index: 318662 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0878. Min Act: -0.0000

Data Index: 151184 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1626376 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0816. Min Act: -0.0000

Data Index: 894328 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0789. Min Act: -0.0000

Data Index: 4614 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0813. Min Act: -0.0000

Data Index: 445600 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0698. Min Act: -0.0000

Data Index: 918683 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0795. Min Act: -0.0000

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1391245 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0786. Min Act: -0.0000

Data Index: 436744 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1445386 (Python Code)

Max Activating Token Index: 359