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

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

Neuron 4481 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1436359 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1502017 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1590286 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1479787 (Python Code)

Max Activating Token Index: 330

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1607262 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1417806 (Python Code)

Max Activating Token Index: 987

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1361650 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1614310 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1566616 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1534279 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1575590 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1638933 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1505375 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1366917 (Python Code)

Max Activating Token Index: 942

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1413987 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1593641 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1574895 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1498092 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1427284 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1515528 (Python Code)

Max Activating Token Index: 716