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

Dataset: The Pile

Neuron 2541 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3914. Min Act: -0.0000

Data Index: 736946 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3360. Min Act: -0.0000

Data Index: 909942 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3123. Min Act: -0.0000

Data Index: 150254 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2955. Min Act: -0.0000

Data Index: 798355 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2938. Min Act: -0.0000

Data Index: 873668 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1886812 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2918. Min Act: -0.0000

Data Index: 157491 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1849864 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1395820 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1762034 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2791. Min Act: -0.0000

Data Index: 720440 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1268331 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1937099 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1212671 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1703490 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2591. Min Act: -0.0000

Data Index: 202307 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2597. Min Act: -0.0000

Data Index: 501002 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2664. Min Act: -0.0000

Data Index: 765476 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1870910 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1188799 (The Pile)

Max Activating Token Index: 149