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

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

Neuron 5195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5698. Min Range: -5.5698

Max Act: 5.5698. Min Act: -0.0001

Data Index: 366871 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 5.5698. Min Range: -5.5698

Max Act: 5.3094. Min Act: 0.0000

Data Index: 373233 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.8607. Min Act: -0.0001

Data Index: 361553 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.8619. Min Act: -0.0000

Data Index: 938967 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.5722. Min Act: -0.0001

Data Index: 1204759 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.5040. Min Act: -0.0001

Data Index: 158048 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.4577. Min Act: -0.0000

Data Index: 183955 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.0626. Min Act: -0.0000

Data Index: 1043144 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.1923. Min Act: 0.0000

Data Index: 642369 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.1825. Min Act: -0.0000

Data Index: 1294914 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.3747. Min Act: -0.0000

Data Index: 277937 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.4720. Min Act: 0.0000

Data Index: 660581 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 5.5698. Min Range: -5.5698

Max Act: 3.8114. Min Act: -0.0001

Data Index: 851604 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.1318. Min Act: -0.0000

Data Index: 87865 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.0869. Min Act: -0.0001

Data Index: 340478 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 5.5698. Min Range: -5.5698

Max Act: 3.8778. Min Act: -0.0000

Data Index: 248162 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.0439. Min Act: -0.0000

Data Index: 952686 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.1972. Min Act: -0.0000

Data Index: 725228 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 5.5698. Min Range: -5.5698

Max Act: 3.8653. Min Act: -0.0001

Data Index: 620904 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 5.5698. Min Range: -5.5698

Max Act: 4.0203. Min Act: 0.0000

Data Index: 1131201 (C4 (Web Text))

Max Activating Token Index: 401