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

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

Neuron 3827 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: 0.3709. Min Range: -0.3709

Max Act: 0.3570. Min Act: -0.0000

Data Index: 720973 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3552. Min Act: -0.0000

Data Index: 908924 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3425. Min Act: -0.0000

Data Index: 586235 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3389. Min Act: -0.0000

Data Index: 958543 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3709. Min Act: -0.0000

Data Index: 251170 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1223714 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1056916 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3331. Min Act: -0.0000

Data Index: 434932 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3146. Min Act: -0.0000

Data Index: 989076 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1160458 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3135. Min Act: -0.0000

Data Index: 192097 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3255. Min Act: -0.0000

Data Index: 850767 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2878. Min Act: -0.0000

Data Index: 963280 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3161. Min Act: -0.0000

Data Index: 71668 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1238003 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2676. Min Act: -0.0000

Data Index: 874104 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2692. Min Act: -0.0000

Data Index: 339117 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2522. Min Act: -0.0000

Data Index: 87616 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1222769 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2679. Min Act: -0.0000

Data Index: 854350 (C4 (Web Text))

Max Activating Token Index: 925