Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 158 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0003

Data Index: 1124780 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0846. Min Act: -0.0003

Data Index: 903535 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1216304 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0853. Min Act: -0.0003

Data Index: 843599 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0821. Min Act: -0.0003

Data Index: 716617 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0813. Min Act: -0.0003

Data Index: 809182 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0829. Min Act: -0.0004

Data Index: 858214 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0829. Min Act: -0.0003

Data Index: 744327 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0809. Min Act: -0.0003

Data Index: 1132898 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0787. Min Act: -0.0003

Data Index: 228998 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1085578 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0800. Min Act: -0.0003

Data Index: 178985 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0827. Min Act: -0.0003

Data Index: 210927 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0819. Min Act: -0.0003

Data Index: 268126 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0811. Min Act: -0.0003

Data Index: 59778 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0794. Min Act: -0.0004

Data Index: 223319 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0779. Min Act: -0.0003

Data Index: 614780 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1058471 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0811. Min Act: -0.0003

Data Index: 273166 (C4 (Web Text))

Max Activating Token Index: 464