Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1594919 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9194. Min Act: -0.0001

Data Index: 1636006 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9697. Min Act: -0.0002

Data Index: 1523484 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9584. Min Act: -0.0001

Data Index: 1390813 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9553. Min Act: -0.0001

Data Index: 1364464 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9208. Min Act: -0.0001

Data Index: 1402533 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9361. Min Act: -0.0002

Data Index: 1539708 (Python Code)

Max Activating Token Index: 610

Text #7

Max Range: 1.0388. Min Range: -1.0388

Max Act: 1.0181. Min Act: -0.0001

Data Index: 1549015 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 1.0388. Min Range: -1.0388

Max Act: 1.0388. Min Act: -0.0001

Data Index: 1568912 (Python Code)

Max Activating Token Index: 561

Text #9

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1497546 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1401807 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9242. Min Act: -0.0001

Data Index: 1501889 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8917. Min Act: -0.0001

Data Index: 1450801 (Python Code)

Max Activating Token Index: 534

Text #13

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9208. Min Act: -0.0001

Data Index: 1549362 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9771. Min Act: -0.0001

Data Index: 1417010 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 1.0388. Min Range: -1.0388

Max Act: 1.0023. Min Act: -0.0001

Data Index: 1532436 (Python Code)

Max Activating Token Index: 743

Text #16

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8766. Min Act: -0.0001

Data Index: 1528872 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1554161 (Python Code)

Max Activating Token Index: 788

Text #18

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8441. Min Act: -0.0001

Data Index: 1520949 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1536774 (Python Code)

Max Activating Token Index: 599