Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0959. Min Act: -0.0001

Data Index: 451093 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0924. Min Act: -0.0001

Data Index: 43479 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0942. Min Act: -0.0002

Data Index: 886117 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1031973 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0920. Min Act: -0.0001

Data Index: 904236 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0884. Min Act: -0.0002

Data Index: 156954 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0888. Min Act: -0.0001

Data Index: 852003 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0836. Min Act: -0.0002

Data Index: 747917 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1180891 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0833. Min Act: -0.0002

Data Index: 614870 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1222660 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0855. Min Act: -0.0002

Data Index: 6334 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1022708 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1068431 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0809. Min Act: -0.0002

Data Index: 865373 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0832. Min Act: -0.0002

Data Index: 99584 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0824. Min Act: -0.0002

Data Index: 12145 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0807. Min Act: -0.0001

Data Index: 103537 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0839. Min Act: -0.0002

Data Index: 743566 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1093649 (C4 (Web Text))

Max Activating Token Index: 869