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

Dataset: The Pile

Neuron 1985 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: 0.2827. Min Range: -0.2827

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1782316 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1442569 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1626981 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2032. Min Act: -0.0000

Data Index: 893081 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1857. Min Act: -0.0000

Data Index: 407387 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1946. Min Act: -0.0000

Data Index: 210369 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1588666 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1052512 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1868464 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1669. Min Act: -0.0000

Data Index: 843050 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1512. Min Act: -0.0000

Data Index: 765353 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1629. Min Act: -0.0000

Data Index: 88864 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1885447 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1672815 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1626. Min Act: -0.0000

Data Index: 762953 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1603. Min Act: -0.0000

Data Index: 433716 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1687445 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1626300 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1608. Min Act: -0.0000

Data Index: 644504 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1300301 (The Pile)

Max Activating Token Index: 974