Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4891 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.4747. Min Act: -0.0000

Data Index: 1481420 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.4775. Min Act: -0.0000

Data Index: 360524 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1434762 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.4719. Min Act: -0.0000

Data Index: 1474025 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1562422 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1409951 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2721. Min Act: -0.0001

Data Index: 1508028 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1622741 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2753. Min Act: -0.0000

Data Index: 1376546 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1593910 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.1756. Min Act: -0.0000

Data Index: 1541453 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1475734 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1582478 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0647. Min Act: 0.0000

Data Index: 1491526 (Python Code)

Max Activating Token Index: 373

Text #14

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1631982 (Python Code)

Max Activating Token Index: 499

Text #15

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1368912 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0526. Min Act: -0.0000

Data Index: 572437 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1426897 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1467075 (Python Code)

Max Activating Token Index: 712

Text #19

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1527879 (Python Code)

Max Activating Token Index: 244