Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 509 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0005

Data Index: 1220479 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0611. Min Act: -0.0005

Data Index: 1300965 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0587. Min Act: -0.0005

Data Index: 312605 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0569. Min Act: -0.0005

Data Index: 663202 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0558. Min Act: -0.0005

Data Index: 31551 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0579. Min Act: -0.0005

Data Index: 1035626 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0536. Min Act: -0.0005

Data Index: 1309065 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0538. Min Act: -0.0005

Data Index: 1328947 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0513. Min Act: -0.0005

Data Index: 1193164 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0533. Min Act: -0.0005

Data Index: 1277046 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1080683 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0534. Min Act: -0.0005

Data Index: 1198791 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0537. Min Act: -0.0005

Data Index: 332077 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0534. Min Act: -0.0005

Data Index: 140305 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0496. Min Act: -0.0005

Data Index: 835175 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0516. Min Act: -0.0005

Data Index: 391811 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0531. Min Act: -0.0005

Data Index: 494578 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0504. Min Act: -0.0005

Data Index: 315126 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0515. Min Act: -0.0005

Data Index: 61169 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0502. Min Act: -0.0005

Data Index: 896044 (C4 (Web Text))

Max Activating Token Index: 464