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

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

Neuron 1072 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.1704. Min Act: -0.0000

Data Index: 186487 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0991. Min Act: -0.0000

Data Index: 969437 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0969. Min Act: -0.0000

Data Index: 279408 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0598. Min Act: -0.0000

Data Index: 617164 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0623. Min Act: -0.0000

Data Index: 14731 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9832. Min Act: -0.0000

Data Index: 315789 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1264922 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1349629 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1067018 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1094359 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9395. Min Act: -0.0000

Data Index: 511298 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9606. Min Act: -0.0000

Data Index: 741882 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8976. Min Act: -0.0000

Data Index: 596389 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1351065 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9037. Min Act: -0.0000

Data Index: 766245 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1292158 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1135122 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9363. Min Act: -0.0000

Data Index: 996523 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9153. Min Act: -0.0000

Data Index: 105553 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8809. Min Act: -0.0000

Data Index: 751506 (C4 (Web Text))

Max Activating Token Index: 968