Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1035 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1854. Min Act: -0.0001

Data Index: 94138 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1861. Min Act: -0.0001

Data Index: 782948 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1796. Min Act: -0.0001

Data Index: 789987 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1790. Min Act: -0.0001

Data Index: 481716 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0001

Data Index: 398368 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1717. Min Act: -0.0001

Data Index: 261709 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1745. Min Act: -0.0001

Data Index: 469342 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1218371 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1655. Min Act: -0.0001

Data Index: 377477 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1710. Min Act: -0.0001

Data Index: 848840 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1749. Min Act: -0.0001

Data Index: 616430 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1665. Min Act: -0.0001

Data Index: 693587 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1652. Min Act: -0.0001

Data Index: 304154 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1018355 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1660. Min Act: -0.0001

Data Index: 886887 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1646. Min Act: -0.0001

Data Index: 768089 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1708. Min Act: -0.0001

Data Index: 997993 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1233971 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1685. Min Act: -0.0001

Data Index: 512852 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1169222 (C4 (Web Text))

Max Activating Token Index: 291