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

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

Neuron 2700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3851. Min Range: -2.3851

Max Act: 2.3851. Min Act: -0.0000

Data Index: 994830 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.9287. Min Act: -0.0000

Data Index: 789061 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.7525. Min Act: -0.0000

Data Index: 13827 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.8201. Min Act: -0.0000

Data Index: 1162778 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1136892 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1076525 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1859. Min Act: -0.0000

Data Index: 26507 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.6747. Min Act: -0.0001

Data Index: 287592 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.3092. Min Act: -0.0000

Data Index: 801730 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.3958. Min Act: -0.0001

Data Index: 283510 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2697. Min Act: -0.0000

Data Index: 387038 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.3356. Min Act: -0.0000

Data Index: 103928 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2608. Min Act: -0.0000

Data Index: 99925 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.0888. Min Act: -0.0001

Data Index: 100619 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1563. Min Act: -0.0000

Data Index: 125260 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.0574. Min Act: -0.0000

Data Index: 851810 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1276764 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.0784. Min Act: -0.0000

Data Index: 439378 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.0708. Min Act: -0.0000

Data Index: 553219 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.0323. Min Act: -0.0000

Data Index: 494631 (C4 (Web Text))

Max Activating Token Index: 987