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

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

Neuron 3464 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1350665 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.2284. Min Act: -0.0000

Data Index: 301878 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1340338 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.1965. Min Act: -0.0000

Data Index: 986395 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.2747. Min Act: -0.0000

Data Index: 785994 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1327160 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.1388. Min Act: -0.0000

Data Index: 188130 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1170106 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1306393 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0902. Min Act: -0.0000

Data Index: 642778 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1039256 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1231057 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0943. Min Act: -0.0000

Data Index: 923748 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1087010 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1620980 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9908. Min Act: 0.0000

Data Index: 244302 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0348. Min Act: -0.0000

Data Index: 479082 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1066034 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1080243 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9179. Min Act: -0.0000

Data Index: 746393 (C4 (Web Text))

Max Activating Token Index: 901