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

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

Neuron 393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5742. Min Act: -0.0001

Data Index: 1079752 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4945. Min Act: -0.0000

Data Index: 163034 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4999. Min Act: -0.0000

Data Index: 617385 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4721. Min Act: -0.0000

Data Index: 802269 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5056. Min Act: -0.0000

Data Index: 817098 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4935. Min Act: -0.0000

Data Index: 144017 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4590. Min Act: -0.0000

Data Index: 860148 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5206. Min Act: -0.0001

Data Index: 286851 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4893. Min Act: -0.0000

Data Index: 445082 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5308. Min Act: -0.0000

Data Index: 405788 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1303803 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5318. Min Act: -0.0000

Data Index: 691115 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1466090 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5385. Min Act: -0.0001

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4529. Min Act: -0.0000

Data Index: 123372 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5355. Min Act: -0.0000

Data Index: 740772 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5240. Min Act: -0.0000

Data Index: 122740 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4820. Min Act: -0.0000

Data Index: 761674 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4563. Min Act: -0.0000

Data Index: 704741 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5066. Min Act: -0.0000

Data Index: 174239 (C4 (Web Text))

Max Activating Token Index: 807