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

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

Neuron 228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1285941 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.7638. Min Act: -0.0000

Data Index: 406765 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1060732 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1143182 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5000. Min Act: -0.0000

Data Index: 479895 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1200686 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5486. Min Act: -0.0000

Data Index: 933815 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1332011 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1053215 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4981. Min Act: -0.0000

Data Index: 299897 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4938. Min Act: -0.0000

Data Index: 388491 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5255. Min Act: -0.0000

Data Index: 168196 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5031. Min Act: -0.0000

Data Index: 157033 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.5011. Min Act: -0.0000

Data Index: 23950 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4859. Min Act: -0.0000

Data Index: 498430 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4790. Min Act: -0.0000

Data Index: 600089 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4728. Min Act: -0.0000

Data Index: 883409 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4640. Min Act: -0.0000

Data Index: 467060 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1225641 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.7751. Min Range: -0.7751

Max Act: 0.4585. Min Act: -0.0000

Data Index: 508346 (C4 (Web Text))

Max Activating Token Index: 450