Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 848 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2394. Min Act: -0.0000

Data Index: 327165 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1901. Min Act: -0.0000

Data Index: 479639 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1760. Min Act: -0.0000

Data Index: 62380 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2035. Min Act: -0.0000

Data Index: 677929 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1356353 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1585. Min Act: -0.0000

Data Index: 906997 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1692. Min Act: -0.0000

Data Index: 596406 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1015311 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1442. Min Act: -0.0000

Data Index: 213145 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1486. Min Act: -0.0000

Data Index: 637178 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1467. Min Act: -0.0000

Data Index: 531820 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1529. Min Act: -0.0000

Data Index: 626781 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1508. Min Act: -0.0000

Data Index: 597203 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1203661 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1303032 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1019829 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1237104 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1412. Min Act: -0.0000

Data Index: 370336 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1458. Min Act: -0.0000

Data Index: 626471 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1493. Min Act: -0.0000

Data Index: 258621 (C4 (Web Text))

Max Activating Token Index: 777