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

Dataset: The Pile

Neuron 1499 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0000

Data Index: 524495 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1178518 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1901769 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1377511 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0716. Min Act: -0.0000

Data Index: 367672 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1786851 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1041695 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0869. Min Act: -0.0000

Data Index: 542290 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1370177 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0766. Min Act: -0.0000

Data Index: 439877 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1876684 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1582323 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0715. Min Act: -0.0000

Data Index: 658756 (The Pile)

Max Activating Token Index: 360

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0814. Min Act: -0.0000

Data Index: 920714 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1986563 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1702772 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1869402 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0761. Min Act: -0.0000

Data Index: 70396 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0761. Min Act: -0.0000

Data Index: 452858 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0720. Min Act: -0.0000

Data Index: 736708 (The Pile)

Max Activating Token Index: 144