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

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

Neuron 787 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: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1333629 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0866. Min Act: -0.0001

Data Index: 322287 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0844. Min Act: -0.0002

Data Index: 458113 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0846. Min Act: -0.0002

Data Index: 257323 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1149845 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0792. Min Act: -0.0002

Data Index: 522833 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0792. Min Act: -0.0002

Data Index: 59580 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0785. Min Act: -0.0002

Data Index: 759870 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1092369 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0770. Min Act: -0.0002

Data Index: 309936 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0764. Min Act: -0.0002

Data Index: 895758 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1283719 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0729. Min Act: -0.0001

Data Index: 628020 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0756. Min Act: -0.0002

Data Index: 182444 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0741. Min Act: -0.0001

Data Index: 191405 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0767. Min Act: -0.0002

Data Index: 934895 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0717. Min Act: -0.0002

Data Index: 557829 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0700. Min Act: -0.0001

Data Index: 747898 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0722. Min Act: -0.0002

Data Index: 529120 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0702. Min Act: -0.0001

Data Index: 380024 (C4 (Web Text))

Max Activating Token Index: 973