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

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

Neuron 4929 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: 0.6885. Min Range: -0.6885

Max Act: 0.6885. Min Act: -0.0000

Data Index: 52997 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6289. Min Act: -0.0000

Data Index: 748013 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6642. Min Act: -0.0000

Data Index: 35514 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6841. Min Act: -0.0000

Data Index: 575343 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1326604 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5698. Min Act: -0.0000

Data Index: 742869 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1285056 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5641. Min Act: -0.0000

Data Index: 533933 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5594. Min Act: -0.0000

Data Index: 971166 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5548. Min Act: -0.0000

Data Index: 561117 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5704. Min Act: -0.0000

Data Index: 23870 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4855. Min Act: -0.0000

Data Index: 532056 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1118306 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4537. Min Act: -0.0000

Data Index: 573851 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1282807 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4546. Min Act: -0.0000

Data Index: 491931 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4406. Min Act: -0.0000

Data Index: 680114 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1033154 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4173. Min Act: -0.0000

Data Index: 537748 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.4329. Min Act: -0.0000

Data Index: 521917 (C4 (Web Text))

Max Activating Token Index: 479