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

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

Neuron 1776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.6868. Min Act: -0.0000

Data Index: 352843 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.2434. Min Act: -0.0000

Data Index: 1430219 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.2553. Min Act: -0.0000

Data Index: 1530863 (Python Code)

Max Activating Token Index: 992

Text #3

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.2632. Min Act: -0.0000

Data Index: 1609774 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1384179 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.2051. Min Act: -0.0000

Data Index: 1464714 (Python Code)

Max Activating Token Index: 979

Text #6

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.1966. Min Act: -0.0000

Data Index: 75913 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1645589 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1549422 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.2515. Min Act: -0.0000

Data Index: 1651922 (Python Code)

Max Activating Token Index: 984

Text #10

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0171. Min Act: -0.0000

Data Index: 1379330 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0743. Min Act: -0.0000

Data Index: 1379566 (Python Code)

Max Activating Token Index: 843

Text #12

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0711. Min Act: -0.0000

Data Index: 1508141 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1648004 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.1656. Min Act: -0.0000

Data Index: 1580399 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0189. Min Act: -0.0000

Data Index: 919669 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1403178 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0187. Min Act: -0.0000

Data Index: 1406863 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.0194. Min Act: -0.0000

Data Index: 1534587 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.1050. Min Act: -0.0000

Data Index: 1617410 (Python Code)

Max Activating Token Index: 111