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

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

Neuron 1989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.1745. Min Act: -0.0000

Data Index: 723640 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.2037. Min Act: -0.0000

Data Index: 541012 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.1572. Min Act: -0.0000

Data Index: 912838 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.0111. Min Act: -0.0000

Data Index: 565792 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.0563. Min Act: -0.0000

Data Index: 111547 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1070869 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.0468. Min Act: -0.0000

Data Index: 546920 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9765. Min Act: -0.0000

Data Index: 826698 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9789. Min Act: -0.0000

Data Index: 240085 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1352170 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1013130 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9464. Min Act: -0.0000

Data Index: 688109 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9495. Min Act: -0.0000

Data Index: 51687 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9448. Min Act: -0.0000

Data Index: 141144 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1148033 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1116323 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9577. Min Act: -0.0000

Data Index: 360531 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9657. Min Act: -0.0000

Data Index: 676774 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9333. Min Act: -0.0000

Data Index: 827528 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8751. Min Act: -0.0000

Data Index: 588247 (C4 (Web Text))

Max Activating Token Index: 711