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

Dataset: The Pile

Neuron 2716 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1461485 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1141685 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1313719 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1258781 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1084059 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0837. Min Act: -0.0000

Data Index: 603741 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1557648 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0744. Min Act: -0.0000

Data Index: 537301 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0780. Min Act: -0.0000

Data Index: 766172 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0765. Min Act: -0.0000

Data Index: 114142 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1685149 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0687. Min Act: -0.0000

Data Index: 411646 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0718. Min Act: -0.0000

Data Index: 566302 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0713. Min Act: -0.0000

Data Index: 726202 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1813036 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1501016 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0712. Min Act: -0.0000

Data Index: 427727 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0664. Min Act: -0.0000

Data Index: 353159 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1150276 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0625. Min Act: -0.0000

Data Index: 974401 (The Pile)

Max Activating Token Index: 975