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

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

Neuron 1160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0001

Data Index: 735464 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0801. Min Act: -0.0001

Data Index: 992462 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0716. Min Act: -0.0001

Data Index: 56838 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0738. Min Act: -0.0001

Data Index: 326483 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1390482 (Python Code)

Max Activating Token Index: 711

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0692. Min Act: -0.0001

Data Index: 577082 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0730. Min Act: -0.0001

Data Index: 100380 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0628. Min Act: -0.0001

Data Index: 894137 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0654. Min Act: -0.0001

Data Index: 185393 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0615. Min Act: -0.0000

Data Index: 970764 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0591. Min Act: -0.0001

Data Index: 208196 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0651. Min Act: -0.0001

Data Index: 967139 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0628. Min Act: -0.0001

Data Index: 731759 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0623. Min Act: -0.0000

Data Index: 747016 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0578. Min Act: -0.0001

Data Index: 238868 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1020230 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1235189 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1131069 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0590. Min Act: -0.0001

Data Index: 56710 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1319816 (C4 (Web Text))

Max Activating Token Index: 637