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

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

Neuron 2069 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.4828. Min Act: -0.0000

Data Index: 440848 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3585. Min Act: -0.0000

Data Index: 642065 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.2792. Min Act: -0.0000

Data Index: 375015 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.2557. Min Act: -0.0000

Data Index: 649887 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.2423. Min Act: -0.0000

Data Index: 276984 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3065. Min Act: -0.0000

Data Index: 743179 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 2.4828. Min Range: -2.4828

Max Act: 1.9376. Min Act: -0.0000

Data Index: 867470 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.1566. Min Act: -0.0000

Data Index: 884029 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.1097. Min Act: -0.0000

Data Index: 669290 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 2.4828. Min Range: -2.4828

Max Act: 1.9438. Min Act: -0.0000

Data Index: 790595 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.1219. Min Act: -0.0000

Data Index: 295414 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.0324. Min Act: -0.0000

Data Index: 1200338 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 2.4828. Min Range: -2.4828

Max Act: 1.9017. Min Act: -0.0000

Data Index: 143781 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.2439. Min Act: -0.0000

Data Index: 1029412 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 2.4828. Min Range: -2.4828

Max Act: 1.9614. Min Act: -0.0000

Data Index: 784282 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.0523. Min Act: -0.0000

Data Index: 1209443 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.0273. Min Act: -0.0000

Data Index: 1035896 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 2.4828. Min Range: -2.4828

Max Act: 1.9302. Min Act: -0.0000

Data Index: 653820 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.0397. Min Act: -0.0000

Data Index: 318750 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.1713. Min Act: -0.0000

Data Index: 1031471 (C4 (Web Text))

Max Activating Token Index: 744