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

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

Neuron 1377 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0763. Min Act: -0.0003

Data Index: 609706 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0740. Min Act: -0.0003

Data Index: 721602 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0751. Min Act: -0.0003

Data Index: 67281 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1214439 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1018764 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0731. Min Act: -0.0003

Data Index: 814935 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0715. Min Act: -0.0003

Data Index: 93461 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0693. Min Act: -0.0003

Data Index: 606979 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0771. Min Act: -0.0003

Data Index: 475336 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0734. Min Act: -0.0003

Data Index: 339695 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1205409 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0652. Min Act: -0.0003

Data Index: 750091 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0717. Min Act: -0.0003

Data Index: 76234 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0663. Min Act: -0.0003

Data Index: 836349 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0687. Min Act: -0.0003

Data Index: 517666 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0679. Min Act: -0.0003

Data Index: 316466 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0660. Min Act: -0.0003

Data Index: 900001 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0709. Min Act: -0.0003

Data Index: 700334 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0683. Min Act: -0.0003

Data Index: 144393 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0681. Min Act: -0.0003

Data Index: 2466 (C4 (Web Text))

Max Activating Token Index: 242