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

Dataset: The Pile

Neuron 2144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.8133. Min Act: -0.0000

Data Index: 91701 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1494805 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.8176. Min Act: -0.0000

Data Index: 159855 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1362651 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1953885 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1286868 (The Pile)

Max Activating Token Index: 790

Text #6

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.7766. Min Act: -0.0000

Data Index: 374385 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.7139. Min Act: -0.0000

Data Index: 866621 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.6886. Min Act: -0.0000

Data Index: 525792 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1665148 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.6857. Min Act: -0.0000

Data Index: 889928 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1559376 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.7455. Min Act: -0.0000

Data Index: 518275 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1906050 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1644142 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1617384 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1383406 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.5770. Min Act: -0.0000

Data Index: 531678 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.5360. Min Act: -0.0000

Data Index: 633788 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1651205 (The Pile)

Max Activating Token Index: 38