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

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

Neuron 4728 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2557. Min Act: -0.0000

Data Index: 619011 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1015705 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1787. Min Act: -0.0000

Data Index: 716185 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1859. Min Act: -0.0000

Data Index: 43638 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1659. Min Act: -0.0000

Data Index: 49486 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1673. Min Act: -0.0000

Data Index: 659418 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1538. Min Act: -0.0000

Data Index: 239912 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1250852 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1377864 (Python Code)

Max Activating Token Index: 721

Text #9

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1316686 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1530. Min Act: -0.0000

Data Index: 192389 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1546. Min Act: -0.0000

Data Index: 941792 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1274. Min Act: -0.0000

Data Index: 270030 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1422. Min Act: -0.0000

Data Index: 561418 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1354. Min Act: -0.0000

Data Index: 165535 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1455. Min Act: -0.0000

Data Index: 457041 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1398. Min Act: -0.0000

Data Index: 825254 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1467. Min Act: -0.0000

Data Index: 590042 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1396. Min Act: -0.0000

Data Index: 787586 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1445. Min Act: -0.0000

Data Index: 771012 (C4 (Web Text))

Max Activating Token Index: 659