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

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

Neuron 2017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1639788 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1468609 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1433191 (Python Code)

Max Activating Token Index: 789

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1413744 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1635916 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1416582 (Python Code)

Max Activating Token Index: 902

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1412629 (Python Code)

Max Activating Token Index: 985

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5723. Min Act: -0.0001

Data Index: 1595287 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1544757 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1566700 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1496942 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1469766 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1593314 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1493761 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1610262 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1497523 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1501669 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1411509 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1406396 (Python Code)

Max Activating Token Index: 390

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1549421 (Python Code)

Max Activating Token Index: 774