Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0888. Min Act: -0.0004

Data Index: 28711 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0878. Min Act: -0.0004

Data Index: 1257435 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0004

Data Index: 792717 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0890. Min Act: -0.0004

Data Index: 836948 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0870. Min Act: -0.0004

Data Index: 771852 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0892. Min Act: -0.0004

Data Index: 539114 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0832. Min Act: -0.0004

Data Index: 693175 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0889. Min Act: -0.0004

Data Index: 478254 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0852. Min Act: -0.0004

Data Index: 1168458 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0845. Min Act: -0.0004

Data Index: 657437 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0807. Min Act: -0.0004

Data Index: 267211 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0867. Min Act: -0.0004

Data Index: 924635 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0771. Min Act: -0.0004

Data Index: 182524 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0771. Min Act: -0.0004

Data Index: 964404 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0826. Min Act: -0.0004

Data Index: 104507 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0857. Min Act: -0.0004

Data Index: 992234 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0793. Min Act: -0.0004

Data Index: 283237 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0817. Min Act: -0.0004

Data Index: 234958 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0759. Min Act: -0.0004

Data Index: 833768 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0757. Min Act: -0.0004

Data Index: 1143786 (C4 (Web Text))

Max Activating Token Index: 190