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

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

Neuron 1998 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: 0.5562. Min Range: -0.5562

Max Act: 0.5292. Min Act: -0.0001

Data Index: 1654387 (Python Code)

Max Activating Token Index: 177

Text #1

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.5299. Min Act: -0.0002

Data Index: 1584419 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.5121. Min Act: -0.0001

Data Index: 1554294 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.5562. Min Act: -0.0002

Data Index: 1564640 (Python Code)

Max Activating Token Index: 667

Text #4

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.5019. Min Act: -0.0002

Data Index: 1532549 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4880. Min Act: -0.0001

Data Index: 1411680 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4864. Min Act: -0.0001

Data Index: 1543617 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4688. Min Act: -0.0002

Data Index: 1479236 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1592571 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4464. Min Act: -0.0002

Data Index: 1640386 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4594. Min Act: -0.0002

Data Index: 1550656 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4455. Min Act: -0.0002

Data Index: 1510127 (Python Code)

Max Activating Token Index: 861

Text #12

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4669. Min Act: -0.0002

Data Index: 1641918 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4594. Min Act: -0.0002

Data Index: 1485155 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4540. Min Act: -0.0001

Data Index: 1649565 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4490. Min Act: -0.0001

Data Index: 1375076 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4383. Min Act: 0.0000

Data Index: 1561041 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1592669 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4375. Min Act: -0.0001

Data Index: 1450637 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4613. Min Act: -0.0001

Data Index: 1651285 (Python Code)

Max Activating Token Index: 983