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

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

Neuron 712 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: 4.1710. Min Range: -4.1710

Max Act: 4.1710. Min Act: -0.0000

Data Index: 708299 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 4.1710. Min Range: -4.1710

Max Act: 4.1697. Min Act: -0.0000

Data Index: 1295122 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.7582. Min Act: -0.0000

Data Index: 581582 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 4.1710. Min Range: -4.1710

Max Act: 4.0913. Min Act: -0.0000

Data Index: 339817 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.7295. Min Act: -0.0000

Data Index: 169380 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.7617. Min Act: -0.0000

Data Index: 220255 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.9241. Min Act: -0.0000

Data Index: 1239526 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.9038. Min Act: -0.0000

Data Index: 958690 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.8664. Min Act: -0.0000

Data Index: 217391 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.9175. Min Act: -0.0000

Data Index: 693366 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.4627. Min Act: -0.0000

Data Index: 944582 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.5481. Min Act: -0.0000

Data Index: 74128 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.4150. Min Act: -0.0000

Data Index: 223711 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.2868. Min Act: -0.0000

Data Index: 1099328 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.1219. Min Act: -0.0000

Data Index: 1059697 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 4.1710. Min Range: -4.1710

Max Act: 2.9454. Min Act: -0.0000

Data Index: 794618 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 4.1710. Min Range: -4.1710

Max Act: 2.9549. Min Act: -0.0000

Data Index: 8316 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.0484. Min Act: -0.0000

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 4.1710. Min Range: -4.1710

Max Act: 3.0222. Min Act: -0.0000

Data Index: 969647 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 4.1710. Min Range: -4.1710

Max Act: 2.7136. Min Act: -0.0000

Data Index: 682639 (C4 (Web Text))

Max Activating Token Index: 269