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

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

Neuron 3293 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1028013 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5824. Min Act: -0.0000

Data Index: 673247 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5620. Min Act: -0.0000

Data Index: 19385 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1144849 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5775. Min Act: -0.0000

Data Index: 845289 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1250823 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1107794 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5137. Min Act: -0.0000

Data Index: 627832 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5062. Min Act: -0.0000

Data Index: 757918 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1255818 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5004. Min Act: -0.0000

Data Index: 659778 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5322. Min Act: -0.0000

Data Index: 724215 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4855. Min Act: -0.0000

Data Index: 431163 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4925. Min Act: -0.0000

Data Index: 359431 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4806. Min Act: -0.0000

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1265801 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4879. Min Act: -0.0000

Data Index: 463698 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5058. Min Act: -0.0000

Data Index: 504021 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4898. Min Act: -0.0000

Data Index: 602292 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1118646 (C4 (Web Text))

Max Activating Token Index: 640