Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1298 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1030. Min Act: -0.0003

Data Index: 530391 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0863. Min Act: -0.0003

Data Index: 1240409 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0829. Min Act: -0.0003

Data Index: 414050 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0884. Min Act: -0.0003

Data Index: 366523 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0848. Min Act: -0.0003

Data Index: 789021 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0842. Min Act: -0.0003

Data Index: 431271 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0874. Min Act: -0.0003

Data Index: 541376 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0859. Min Act: -0.0003

Data Index: 1326391 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0868. Min Act: -0.0003

Data Index: 855158 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0879. Min Act: -0.0003

Data Index: 664157 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0840. Min Act: -0.0003

Data Index: 512135 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0902. Min Act: -0.0003

Data Index: 708093 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0811. Min Act: -0.0003

Data Index: 873951 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0794. Min Act: -0.0003

Data Index: 927841 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0867. Min Act: -0.0003

Data Index: 1164784 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0827. Min Act: -0.0003

Data Index: 526404 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0826. Min Act: -0.0003

Data Index: 891134 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0854. Min Act: -0.0003

Data Index: 723233 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0848. Min Act: -0.0003

Data Index: 955458 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0867. Min Act: -0.0003

Data Index: 742427 (C4 (Web Text))

Max Activating Token Index: 517