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

Dataset: The Pile

Neuron 4672 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: 1.2758. Min Range: -1.2758

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1192321 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1435166 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.1656. Min Act: -0.0000

Data Index: 439718 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1777165 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1284902 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1302634 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1949343 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.0639. Min Act: -0.0000

Data Index: 719203 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1640180 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.0595. Min Act: -0.0000

Data Index: 685052 (The Pile)

Max Activating Token Index: 659

Text #10

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1409342 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1699386 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1763652 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1750379 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.9703. Min Act: -0.0000

Data Index: 973726 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 1.2758. Min Range: -1.2758

Max Act: 1.0200. Min Act: -0.0000

Data Index: 158890 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.9367. Min Act: -0.0000

Data Index: 947714 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.8928. Min Act: -0.0000

Data Index: 679661 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.9172. Min Act: -0.0000

Data Index: 961319 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 1.2758. Min Range: -1.2758

Max Act: 0.9924. Min Act: -0.0000

Data Index: 769018 (The Pile)

Max Activating Token Index: 800