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

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

Neuron 2290 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: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0003

Data Index: 279412 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0926. Min Act: -0.0003

Data Index: 456629 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1002. Min Act: -0.0003

Data Index: 322055 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0945. Min Act: -0.0003

Data Index: 415014 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0810. Min Act: -0.0003

Data Index: 409032 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0906. Min Act: -0.0003

Data Index: 351552 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1312078 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1239897 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0823. Min Act: -0.0003

Data Index: 117206 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0836. Min Act: -0.0003

Data Index: 184526 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0836. Min Act: -0.0003

Data Index: 522149 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1358306 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0798. Min Act: -0.0003

Data Index: 245435 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0804. Min Act: -0.0003

Data Index: 792966 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0814. Min Act: -0.0003

Data Index: 896088 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0774. Min Act: -0.0003

Data Index: 531920 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0802. Min Act: -0.0003

Data Index: 25802 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1216906 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0859. Min Act: -0.0003

Data Index: 1278628 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1141486 (C4 (Web Text))

Max Activating Token Index: 55