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

Dataset: The Pile

Neuron 3385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1121432 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1801. Min Act: -0.0000

Data Index: 661043 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1836. Min Act: -0.0000

Data Index: 391914 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1767. Min Act: -0.0000

Data Index: 191466 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1422714 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1527. Min Act: -0.0000

Data Index: 193120 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.2067. Min Act: -0.0000

Data Index: 56191 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1459. Min Act: -0.0000

Data Index: 30099 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1779. Min Act: -0.0000

Data Index: 329822 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1773. Min Act: -0.0000

Data Index: 972973 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1675841 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1554. Min Act: -0.0000

Data Index: 47177 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1895. Min Act: -0.0000

Data Index: 545763 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1396. Min Act: -0.0000

Data Index: 922278 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1147526 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1700. Min Act: -0.0000

Data Index: 697403 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1792. Min Act: -0.0000

Data Index: 358991 (The Pile)

Max Activating Token Index: 473

Text #17

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1850035 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1572. Min Act: -0.0000

Data Index: 515452 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1183714 (The Pile)

Max Activating Token Index: 352