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

Dataset: The Pile

Neuron 1035 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: 0.6562. Min Range: -0.6562

Max Act: 0.6562. Min Act: -0.0000

Data Index: 181008 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1486128 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5585. Min Act: -0.0000

Data Index: 318589 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5661. Min Act: -0.0000

Data Index: 748404 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5496. Min Act: -0.0000

Data Index: 384313 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5666. Min Act: -0.0000

Data Index: 995822 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1733690 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6193. Min Act: -0.0000

Data Index: 976421 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5702. Min Act: -0.0000

Data Index: 16869 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1531314 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1040431 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5067. Min Act: -0.0000

Data Index: 461121 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4601. Min Act: -0.0000

Data Index: 264118 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5156. Min Act: -0.0000

Data Index: 117530 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1061008 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1436903 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1071040 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5052. Min Act: -0.0000

Data Index: 655681 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1919101 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1345809 (The Pile)

Max Activating Token Index: 154