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

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

Neuron 3300 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: 0.1874. Min Range: -0.1874

Max Act: 0.1779. Min Act: -0.0000

Data Index: 494512 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1307745 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1859. Min Act: -0.0000

Data Index: 294059 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1867. Min Act: -0.0000

Data Index: 681929 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1240769 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1835. Min Act: -0.0000

Data Index: 369166 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1775. Min Act: -0.0000

Data Index: 587981 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1326388 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1762. Min Act: -0.0000

Data Index: 527037 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1595. Min Act: -0.0000

Data Index: 155143 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1156. Min Act: -0.0000

Data Index: 526328 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1085. Min Act: -0.0000

Data Index: 667982 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.0993. Min Act: -0.0000

Data Index: 560387 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1031. Min Act: -0.0000

Data Index: 922702 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.0967. Min Act: -0.0000

Data Index: 524894 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1065. Min Act: -0.0000

Data Index: 296806 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1067. Min Act: -0.0000

Data Index: 616102 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1024. Min Act: -0.0000

Data Index: 303056 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.0983. Min Act: -0.0000

Data Index: 563742 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1018. Min Act: -0.0000

Data Index: 980825 (C4 (Web Text))

Max Activating Token Index: 695