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

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

Neuron 1490 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: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1279281 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0912. Min Act: -0.0003

Data Index: 322449 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0851. Min Act: -0.0003

Data Index: 478613 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0902. Min Act: -0.0003

Data Index: 869438 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0817. Min Act: -0.0003

Data Index: 258299 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0830. Min Act: -0.0003

Data Index: 948145 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0769. Min Act: -0.0003

Data Index: 330652 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1011996 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0818. Min Act: -0.0003

Data Index: 505963 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0770. Min Act: -0.0003

Data Index: 669238 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1270640 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0761. Min Act: -0.0003

Data Index: 1120769 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1268301 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0811. Min Act: -0.0003

Data Index: 887529 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1073274 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0801. Min Act: -0.0003

Data Index: 762055 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1066523 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0771. Min Act: -0.0003

Data Index: 8790 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0796. Min Act: -0.0003

Data Index: 549616 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0735. Min Act: -0.0003

Data Index: 587131 (C4 (Web Text))

Max Activating Token Index: 168