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

Dataset: The Pile

Neuron 4808 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1360693 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1819986 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1033296 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1308681 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7904. Min Act: -0.0000

Data Index: 98273 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1697168 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7576. Min Act: -0.0000

Data Index: 794382 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1229100 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1206287 (The Pile)

Max Activating Token Index: 827

Text #9

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6787. Min Act: -0.0000

Data Index: 536533 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7600. Min Act: -0.0000

Data Index: 531743 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1385446 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1771291 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7283. Min Act: -0.0000

Data Index: 922720 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1708177 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6745. Min Act: -0.0000

Data Index: 871409 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6788. Min Act: 0.0001

Data Index: 1309411 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1293048 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1610987 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6813. Min Act: 0.0000

Data Index: 67803 (The Pile)

Max Activating Token Index: 940