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

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

Neuron 3894 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: 1.8817. Min Range: -1.8817

Max Act: 1.8501. Min Act: -0.0001

Data Index: 1296903 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.8449. Min Act: -0.0001

Data Index: 1321295 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.7396. Min Act: -0.0001

Data Index: 848330 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.8817. Min Act: -0.0001

Data Index: 1061716 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.7519. Min Act: -0.0001

Data Index: 445863 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.7004. Min Act: -0.0001

Data Index: 425801 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5684. Min Act: -0.0001

Data Index: 329163 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5723. Min Act: -0.0001

Data Index: 1097309 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5486. Min Act: -0.0001

Data Index: 776685 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5557. Min Act: -0.0001

Data Index: 892699 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4540. Min Act: -0.0001

Data Index: 1159936 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5722. Min Act: -0.0001

Data Index: 339410 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4877. Min Act: -0.0001

Data Index: 437893 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5836. Min Act: -0.0001

Data Index: 285141 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4414. Min Act: -0.0001

Data Index: 1209571 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.3974. Min Act: -0.0001

Data Index: 1122093 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4580. Min Act: -0.0001

Data Index: 80292 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4048. Min Act: -0.0001

Data Index: 243815 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4101. Min Act: -0.0001

Data Index: 923653 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4748. Min Act: -0.0001

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 302