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

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

Neuron 4961 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: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1496907 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1537520 (Python Code)

Max Activating Token Index: 859

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1587799 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0864. Min Act: -0.0002

Data Index: 737688 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1438291 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1545991 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1410535 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1534498 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1585413 (Python Code)

Max Activating Token Index: 582

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1556905 (Python Code)

Max Activating Token Index: 531

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1389820 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1549846 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0743. Min Act: -0.0002

Data Index: 166231 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1440428 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1623386 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1437936 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1576850 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1542744 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1583200 (Python Code)

Max Activating Token Index: 871