Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2098 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1731. Min Range: -2.1731

Max Act: 2.1731. Min Act: -0.0000

Data Index: 879995 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1441437 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1406232 (Python Code)

Max Activating Token Index: 556

Text #3

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1485875 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1429837 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1397445 (Python Code)

Max Activating Token Index: 679

Text #6

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1545600 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.3856. Min Act: -0.0000

Data Index: 911741 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1587062 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1389176 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.3742. Min Act: -0.0000

Data Index: 1555384 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1575017 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1363687 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1604114 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1595300 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1364072 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1407443 (Python Code)

Max Activating Token Index: 805

Text #17

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1641058 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1431911 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 2.1731. Min Range: -2.1731

Max Act: 1.1227. Min Act: -0.0000

Data Index: 833857 (C4 (Web Text))

Max Activating Token Index: 15