Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3268 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1208068 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0813. Min Act: -0.0001

Data Index: 501771 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0864. Min Act: -0.0001

Data Index: 914449 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0793. Min Act: -0.0001

Data Index: 767680 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0854. Min Act: -0.0001

Data Index: 515797 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0784. Min Act: -0.0001

Data Index: 399790 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1228743 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1312275 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0792. Min Act: -0.0001

Data Index: 301014 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0682. Min Act: -0.0001

Data Index: 308100 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0772. Min Act: -0.0001

Data Index: 882020 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0750. Min Act: -0.0001

Data Index: 60297 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0826. Min Act: -0.0001

Data Index: 619543 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1301691 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1321203 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0741. Min Act: -0.0001

Data Index: 534053 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0727. Min Act: -0.0001

Data Index: 420400 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0693. Min Act: -0.0001

Data Index: 875618 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1240703 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0730. Min Act: -0.0001

Data Index: 145323 (C4 (Web Text))

Max Activating Token Index: 344