Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4679 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.3673. Min Act: -0.0000

Data Index: 1329983 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.3040. Min Act: -0.0000

Data Index: 971566 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2860. Min Act: -0.0000

Data Index: 460818 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1049308 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1280343 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2150. Min Act: -0.0000

Data Index: 64317 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1198660 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1175362 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1714. Min Act: -0.0000

Data Index: 791870 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1042622 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2217. Min Act: -0.0000

Data Index: 36266 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1034638 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1346661 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1810. Min Act: -0.0000

Data Index: 55195 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1259138 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1552. Min Act: -0.0000

Data Index: 753866 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1020. Min Act: -0.0000

Data Index: 189611 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.1459. Min Act: -0.0000

Data Index: 133299 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.0148. Min Act: -0.0000

Data Index: 143086 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.3673. Min Range: -1.3673

Max Act: 1.0173. Min Act: -0.0000

Data Index: 801413 (C4 (Web Text))

Max Activating Token Index: 24