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

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

Neuron 1783 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: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1131746 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0607. Min Act: -0.0003

Data Index: 554601 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0583. Min Act: -0.0004

Data Index: 985724 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0572. Min Act: -0.0003

Data Index: 544616 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0570. Min Act: -0.0003

Data Index: 753800 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1172819 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0543. Min Act: -0.0003

Data Index: 218680 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0531. Min Act: -0.0003

Data Index: 610949 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0515. Min Act: -0.0004

Data Index: 1130554 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0512. Min Act: -0.0003

Data Index: 536934 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0515. Min Act: -0.0003

Data Index: 890726 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0501. Min Act: -0.0004

Data Index: 1005532 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0503. Min Act: -0.0003

Data Index: 766249 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0497. Min Act: -0.0003

Data Index: 322165 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0479. Min Act: -0.0003

Data Index: 864190 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0488. Min Act: -0.0003

Data Index: 900843 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0494. Min Act: -0.0004

Data Index: 569803 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1168616 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0480. Min Act: -0.0004

Data Index: 789968 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0475. Min Act: -0.0003

Data Index: 723260 (C4 (Web Text))

Max Activating Token Index: 540