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

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

Neuron 3529 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: 0.1720. Min Range: -0.1720

Max Act: 0.1720. Min Act: -0.0001

Data Index: 949743 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1515. Min Act: -0.0001

Data Index: 458868 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1392175 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1431792 (Python Code)

Max Activating Token Index: 882

Text #4

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1443276 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1430605 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1408573 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1107515 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1524987 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1651007 (Python Code)

Max Activating Token Index: 764

Text #10

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1449893 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1607161 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1599792 (Python Code)

Max Activating Token Index: 499

Text #13

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1525583 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1457121 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1457760 (Python Code)

Max Activating Token Index: 506

Text #16

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1380855 (Python Code)

Max Activating Token Index: 515

Text #17

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1408062 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1577693 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1639483 (Python Code)

Max Activating Token Index: 150