Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1389 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3538. Min Act: -0.0001

Data Index: 928312 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2684. Min Act: -0.0001

Data Index: 459339 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2873. Min Act: -0.0001

Data Index: 685604 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2205. Min Act: -0.0001

Data Index: 543415 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2423. Min Act: -0.0001

Data Index: 466263 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1509. Min Act: -0.0001

Data Index: 358376 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1954. Min Act: -0.0001

Data Index: 61828 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2102. Min Act: -0.0001

Data Index: 323922 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1812. Min Act: -0.0001

Data Index: 181520 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1248399 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1892. Min Act: -0.0001

Data Index: 623526 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1918. Min Act: -0.0001

Data Index: 271910 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1780. Min Act: -0.0001

Data Index: 869535 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1217976 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1774. Min Act: -0.0001

Data Index: 751517 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1793. Min Act: -0.0001

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1701. Min Act: -0.0001

Data Index: 896686 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1801. Min Act: -0.0001

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1247515 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1787. Min Act: -0.0001

Data Index: 125617 (C4 (Web Text))

Max Activating Token Index: 32