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

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

Neuron 1343 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: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1644791 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1624808 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1635638 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1531200 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1510093 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1482734 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1466863 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1406234 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1592726 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1423457 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1492788 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1581939 (Python Code)

Max Activating Token Index: 589

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0743. Min Act: -0.0002

Data Index: 113449 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0703. Min Act: -0.0002

Data Index: 789435 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1432940 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1615183 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0731. Min Act: -0.0002

Data Index: 375782 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1544937 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1589973 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1563479 (Python Code)

Max Activating Token Index: 54