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

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

Neuron 5635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.5074. Min Act: -0.0000

Data Index: 1317737 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.5608. Min Act: -0.0000

Data Index: 181527 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.3738. Min Act: -0.0000

Data Index: 168575 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.3092. Min Act: -0.0000

Data Index: 225769 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.0932. Min Act: -0.0000

Data Index: 186158 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.1787. Min Act: -0.0000

Data Index: 113088 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.0056. Min Act: -0.0000

Data Index: 359681 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.9920. Min Act: -0.0000

Data Index: 844184 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.8311. Min Act: -0.0000

Data Index: 780740 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.1214. Min Act: -0.0000

Data Index: 1006083 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1149925 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.0955. Min Act: -0.0000

Data Index: 809338 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.9539. Min Act: -0.0000

Data Index: 886629 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.9317. Min Act: -0.0000

Data Index: 227372 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.9175. Min Act: -0.0000

Data Index: 175369 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 3.5608. Min Range: -3.5608

Max Act: 3.0715. Min Act: -0.0000

Data Index: 94635 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.7401. Min Act: -0.0000

Data Index: 345874 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.8493. Min Act: -0.0000

Data Index: 836219 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.7240. Min Act: -0.0000

Data Index: 541924 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 3.5608. Min Range: -3.5608

Max Act: 2.8254. Min Act: -0.0000

Data Index: 303485 (C4 (Web Text))

Max Activating Token Index: 802