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

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

Neuron 3401 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0978. Min Range: -1.0978

Max Act: 1.0978. Min Act: -0.0000

Data Index: 548677 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 1.0978. Min Range: -1.0978

Max Act: 1.0486. Min Act: -0.0000

Data Index: 211808 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.9510. Min Act: -0.0000

Data Index: 826688 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1253097 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.9191. Min Act: -0.0000

Data Index: 916907 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.9455. Min Act: -0.0000

Data Index: 582383 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1172443 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7876. Min Act: -0.0000

Data Index: 389128 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7637. Min Act: -0.0000

Data Index: 800512 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7771. Min Act: -0.0000

Data Index: 62767 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1151534 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7851. Min Act: -0.0000

Data Index: 224952 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7590. Min Act: -0.0000

Data Index: 792946 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7748. Min Act: -0.0000

Data Index: 350752 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7220. Min Act: -0.0000

Data Index: 464960 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1104416 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.7306. Min Act: 0.0000

Data Index: 827033 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.6829. Min Act: -0.0000

Data Index: 347219 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.6778. Min Act: -0.0000

Data Index: 709403 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.0978. Min Range: -1.0978

Max Act: 0.6918. Min Act: -0.0000

Data Index: 671281 (C4 (Web Text))

Max Activating Token Index: 378