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

Dataset: The Pile

Neuron 587 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1652173 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1910439 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3294. Min Act: -0.0000

Data Index: 167244 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1993707 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1765. Min Act: -0.0000

Data Index: 884789 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1219443 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1905. Min Act: -0.0000

Data Index: 310797 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1895570 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1572410 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1573781 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1810061 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1679607 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1588. Min Act: -0.0000

Data Index: 670188 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1840752 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1519. Min Act: -0.0000

Data Index: 223511 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1381. Min Act: -0.0000

Data Index: 383742 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1456. Min Act: -0.0000

Data Index: 905020 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1235838 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1402. Min Act: -0.0000

Data Index: 23734 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.1631. Min Act: -0.0000

Data Index: 705046 (The Pile)

Max Activating Token Index: 675