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

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

Neuron 4241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.7571. Min Act: -0.0001

Data Index: 1493214 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5950. Min Act: -0.0000

Data Index: 1482083 (Python Code)

Max Activating Token Index: 998

Text #2

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5951. Min Act: -0.0000

Data Index: 1608288 (Python Code)

Max Activating Token Index: 665

Text #3

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1370891 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1448623 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1574014 (Python Code)

Max Activating Token Index: 884

Text #6

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1614253 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4229. Min Act: -0.0000

Data Index: 1564235 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5101. Min Act: -0.0001

Data Index: 1652085 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1400874 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1644706 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3448. Min Act: -0.0001

Data Index: 1413884 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1378165 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1501830 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3890. Min Act: -0.0000

Data Index: 1584477 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1466781 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1460183 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1650932 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1527072 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1600915 (Python Code)

Max Activating Token Index: 523