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

Dataset: The Pile

Neuron 666 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: 0.7857. Min Range: -0.7857

Max Act: 0.7857. Min Act: -0.0000

Data Index: 747907 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6833. Min Act: 0.0000

Data Index: 1338856 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6646. Min Act: -0.0000

Data Index: 807838 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1109381 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1323574 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6955. Min Act: -0.0000

Data Index: 133168 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1575428 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1843341 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1780444 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6826. Min Act: 0.0000

Data Index: 1718959 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6023. Min Act: 0.0000

Data Index: 1652882 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6061. Min Act: -0.0000

Data Index: 980778 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1453610 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1043572 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5346. Min Act: -0.0000

Data Index: 716196 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5684. Min Act: 0.0000

Data Index: 1143892 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5819. Min Act: -0.0000

Data Index: 933292 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5823. Min Act: 0.0000

Data Index: 1203966 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5538. Min Act: -0.0000

Data Index: 283283 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1890218 (The Pile)

Max Activating Token Index: 46