Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1672 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1388230 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1535924 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1648341 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1431906 (Python Code)

Max Activating Token Index: 623

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0763. Min Act: 0.0001

Data Index: 1514562 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0738. Min Act: 0.0002

Data Index: 1448126 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1543049 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1638825 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0720. Min Act: 0.0001

Data Index: 1451031 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1645737 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0729. Min Act: 0.0002

Data Index: 1391810 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1406979 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0730. Min Act: 0.0001

Data Index: 1552963 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0707. Min Act: 0.0001

Data Index: 1377335 (Python Code)

Max Activating Token Index: 611

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1403871 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1606523 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0693. Min Act: 0.0001

Data Index: 1456044 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1470462 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0683. Min Act: 0.0002

Data Index: 1557755 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1420691 (Python Code)

Max Activating Token Index: 264