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

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

Neuron 409 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: 0.1880. Min Range: -0.1880

Max Act: 0.1880. Min Act: -0.0001

Data Index: 1331542 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1086339 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1317831 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1870. Min Act: -0.0000

Data Index: 247908 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1762. Min Act: -0.0000

Data Index: 767732 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1780. Min Act: -0.0000

Data Index: 654071 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1716. Min Act: -0.0000

Data Index: 527906 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1709. Min Act: -0.0000

Data Index: 775084 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1720. Min Act: -0.0000

Data Index: 387584 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1654. Min Act: -0.0000

Data Index: 485777 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1656. Min Act: -0.0000

Data Index: 551639 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1649. Min Act: -0.0000

Data Index: 630272 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1684. Min Act: -0.0001

Data Index: 269157 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1620. Min Act: -0.0000

Data Index: 302027 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1610. Min Act: -0.0001

Data Index: 297487 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1530. Min Act: -0.0001

Data Index: 22249 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1000363 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1190663 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1135598 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1230543 (C4 (Web Text))

Max Activating Token Index: 997