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

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

Neuron 1445 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: 0.0991. Min Range: -0.0991

Max Act: 0.0974. Min Act: -0.0004

Data Index: 261547 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0003

Data Index: 907364 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1244193 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0888. Min Act: -0.0003

Data Index: 204570 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0875. Min Act: -0.0003

Data Index: 856459 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0852. Min Act: -0.0003

Data Index: 134356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0902. Min Act: -0.0003

Data Index: 173612 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0853. Min Act: -0.0003

Data Index: 595511 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0862. Min Act: -0.0004

Data Index: 1079351 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0854. Min Act: -0.0003

Data Index: 229681 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0880. Min Act: -0.0002

Data Index: 981914 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0857. Min Act: -0.0003

Data Index: 392139 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0922. Min Act: -0.0003

Data Index: 1261125 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0859. Min Act: -0.0003

Data Index: 1170361 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1241134 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0838. Min Act: -0.0003

Data Index: 1343656 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0863. Min Act: -0.0003

Data Index: 346784 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1326361 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0836. Min Act: -0.0003

Data Index: 766921 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0822. Min Act: -0.0004

Data Index: 17360 (C4 (Web Text))

Max Activating Token Index: 418