Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 874 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1477. Min Act: -0.0002

Data Index: 758732 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1148. Min Act: -0.0002

Data Index: 314102 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0961. Min Act: -0.0002

Data Index: 549976 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0942. Min Act: -0.0001

Data Index: 243782 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0898. Min Act: 0.0002

Data Index: 867702 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0914. Min Act: 0.0000

Data Index: 1077452 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0879. Min Act: -0.0002

Data Index: 373771 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1110898 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1247341 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0923. Min Act: -0.0002

Data Index: 830701 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0859. Min Act: -0.0002

Data Index: 670371 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0886. Min Act: -0.0001

Data Index: 998854 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1211978 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0848. Min Act: -0.0002

Data Index: 206334 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0841. Min Act: -0.0002

Data Index: 522859 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1085735 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0825. Min Act: -0.0001

Data Index: 108958 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0819. Min Act: 0.0000

Data Index: 55930 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0817. Min Act: -0.0000

Data Index: 951551 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1059235 (C4 (Web Text))

Max Activating Token Index: 174