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

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

Neuron 575 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1460473 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1609339 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1425260 (Python Code)

Max Activating Token Index: 879

Text #3

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4582. Min Act: -0.0000

Data Index: 1464659 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1427061 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4188. Min Act: -0.0000

Data Index: 1533487 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1462778 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1453422 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1647696 (Python Code)

Max Activating Token Index: 706

Text #9

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2353. Min Act: -0.0001

Data Index: 1548553 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1651894 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.1973. Min Act: -0.0001

Data Index: 1555975 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1389764 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2523. Min Act: -0.0001

Data Index: 1581548 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1376555 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1502963 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2070. Min Act: -0.0001

Data Index: 1576808 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1627271 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1382583 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1381373 (Python Code)

Max Activating Token Index: 616