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

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

Neuron 3075 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: 0.7828. Min Range: -0.7828

Max Act: 0.7828. Min Act: -0.0000

Data Index: 908364 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1081163 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.6568. Min Act: -0.0000

Data Index: 847253 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.6219. Min Act: -0.0000

Data Index: 390710 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1109475 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1053529 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.6059. Min Act: 0.0000

Data Index: 593851 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.6221. Min Act: -0.0000

Data Index: 572915 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1293909 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5811. Min Act: -0.0000

Data Index: 871733 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5854. Min Act: -0.0000

Data Index: 526486 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5983. Min Act: -0.0000

Data Index: 752381 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5511. Min Act: -0.0000

Data Index: 789364 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5646. Min Act: 0.0000

Data Index: 782820 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1359654 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5520. Min Act: 0.0000

Data Index: 183548 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1034279 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1189457 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1285417 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.7828. Min Range: -0.7828

Max Act: 0.5336. Min Act: -0.0000

Data Index: 873529 (C4 (Web Text))

Max Activating Token Index: 546