Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.9899. Min Act: -0.0000

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.6818. Min Act: -0.0000

Data Index: 221275 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.2415. Min Act: -0.0000

Data Index: 500260 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0936. Min Act: -0.0000

Data Index: 134707 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.2201. Min Act: -0.0000

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.1118. Min Act: -0.0000

Data Index: 548719 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0886. Min Act: -0.0000

Data Index: 714024 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.9899. Min Range: -1.9899

Max Act: 0.9720. Min Act: -0.0000

Data Index: 311356 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.1049. Min Act: -0.0000

Data Index: 812916 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.9899. Min Range: -1.9899

Max Act: 0.9995. Min Act: -0.0000

Data Index: 437714 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.1660. Min Act: -0.0000

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0890. Min Act: -0.0000

Data Index: 614301 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0021. Min Act: -0.0000

Data Index: 25322 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.9899. Min Range: -1.9899

Max Act: 0.8898. Min Act: -0.0000

Data Index: 27843 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1107248 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0518. Min Act: -0.0000

Data Index: 205791 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.9899. Min Range: -1.9899

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1036206 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.9899. Min Range: -1.9899

Max Act: 0.9476. Min Act: -0.0000

Data Index: 11140 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.9899. Min Range: -1.9899

Max Act: 0.9163. Min Act: -0.0000

Data Index: 249550 (C4 (Web Text))

Max Activating Token Index: 998