Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3671 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0024. Min Act: -0.0003

Data Index: 533287 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0003

Data Index: 145989 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1268574 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1316710 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1382013 (Python Code)

Max Activating Token Index: 560

Text #6

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0002

Data Index: 139836 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0019. Min Act: -0.0002

Data Index: 27986 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1484213 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1477334 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0018. Min Act: -0.0002

Data Index: 743102 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0002

Data Index: 501997 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0018. Min Act: -0.0002

Data Index: 109365 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0002

Data Index: 1471420 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0016. Min Act: -0.0003

Data Index: 696916 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0002

Data Index: 894107 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0002

Data Index: 611290 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1049154 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0003

Data Index: 415100 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0002

Data Index: 184861 (C4 (Web Text))

Max Activating Token Index: 235