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

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

Neuron 3395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1474640 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1628546 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1020394 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1438417 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1573548 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1499047 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1639036 (Python Code)

Max Activating Token Index: 851

Text #7

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1532459 (Python Code)

Max Activating Token Index: 447

Text #8

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1434596 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1538711 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1587012 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1480108 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1540440 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1638207 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1500150 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1422737 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1609663 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1635431 (Python Code)

Max Activating Token Index: 891

Text #18

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.5707. Min Act: -0.0000

Data Index: 774491 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1411384 (Python Code)

Max Activating Token Index: 642