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

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

Neuron 175 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2090. Min Range: -2.2090

Max Act: 2.2090. Min Act: -0.0000

Data Index: 1331444 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 2.2090. Min Range: -2.2090

Max Act: 2.2018. Min Act: -0.0000

Data Index: 127872 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 2.2090. Min Range: -2.2090

Max Act: 2.0570. Min Act: -0.0000

Data Index: 173011 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 2.2090. Min Range: -2.2090

Max Act: 2.1906. Min Act: -0.0000

Data Index: 662040 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 2.2090. Min Range: -2.2090

Max Act: 2.0119. Min Act: 0.0000

Data Index: 1310476 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.9012. Min Act: -0.0000

Data Index: 491850 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.9814. Min Act: -0.0000

Data Index: 360607 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1298330 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.9023. Min Act: -0.0000

Data Index: 1104743 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8933. Min Act: -0.0000

Data Index: 479495 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 2.2090. Min Range: -2.2090

Max Act: 2.0018. Min Act: -0.0000

Data Index: 938584 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8795. Min Act: -0.0000

Data Index: 1315929 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8626. Min Act: -0.0000

Data Index: 519693 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8417. Min Act: -0.0000

Data Index: 671640 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1247460 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8328. Min Act: -0.0000

Data Index: 1141658 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.9293. Min Act: -0.0000

Data Index: 533783 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.9298. Min Act: -0.0000

Data Index: 205200 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8158. Min Act: -0.0000

Data Index: 1177409 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.2090. Min Range: -2.2090

Max Act: 1.8127. Min Act: -0.0000

Data Index: 725773 (C4 (Web Text))

Max Activating Token Index: 445