Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3133 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 6.1516. Min Range: -6.1516

Max Act: 6.0675. Min Act: -0.0001

Data Index: 1006219 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 6.1516. Min Range: -6.1516

Max Act: 6.1516. Min Act: -0.0001

Data Index: 816612 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 6.1516. Min Range: -6.1516

Max Act: 6.1342. Min Act: -0.0001

Data Index: 990676 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 6.1516. Min Range: -6.1516

Max Act: 6.0670. Min Act: -0.0001

Data Index: 523382 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.8415. Min Act: -0.0001

Data Index: 744966 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.6959. Min Act: -0.0001

Data Index: 546756 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.6530. Min Act: -0.0001

Data Index: 888949 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.4223. Min Act: -0.0001

Data Index: 90241 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.4035. Min Act: -0.0001

Data Index: 746828 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.2733. Min Act: -0.0001

Data Index: 181615 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 6.1516. Min Range: -6.1516

Max Act: 4.8778. Min Act: -0.0001

Data Index: 1333210 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.0128. Min Act: -0.0001

Data Index: 274616 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 6.1516. Min Range: -6.1516

Max Act: 4.9826. Min Act: -0.0001

Data Index: 756921 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.2552. Min Act: -0.0001

Data Index: 241753 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.2316. Min Act: -0.0001

Data Index: 807439 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.3341. Min Act: -0.0001

Data Index: 10653 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.0378. Min Act: -0.0001

Data Index: 723668 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.1520. Min Act: -0.0001

Data Index: 402475 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 6.1516. Min Range: -6.1516

Max Act: 5.0900. Min Act: -0.0001

Data Index: 702578 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 6.1516. Min Range: -6.1516

Max Act: 4.3672. Min Act: -0.0001

Data Index: 819288 (C4 (Web Text))

Max Activating Token Index: 911