Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5024 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.5484. Min Range: -6.5484

Max Act: 6.4275. Min Act: -0.0000

Data Index: 1266827 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 6.5484. Min Range: -6.5484

Max Act: 6.5469. Min Act: -0.0000

Data Index: 1313075 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 6.5484. Min Range: -6.5484

Max Act: 6.5484. Min Act: -0.0000

Data Index: 496812 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.4727. Min Act: -0.0000

Data Index: 218937 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.6918. Min Act: -0.0000

Data Index: 511348 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.3984. Min Act: -0.0000

Data Index: 279273 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.0501. Min Act: -0.0000

Data Index: 646357 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.4649. Min Act: -0.0000

Data Index: 1337307 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.0766. Min Act: -0.0000

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.4195. Min Act: -0.0000

Data Index: 1002641 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.6392. Min Act: -0.0000

Data Index: 547355 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.5856. Min Act: -0.0000

Data Index: 1157659 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.1612. Min Act: -0.0000

Data Index: 28744 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 6.5484. Min Range: -6.5484

Max Act: 5.6392. Min Act: -0.0000

Data Index: 325779 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 6.5484. Min Range: -6.5484

Max Act: 3.5422. Min Act: -0.0000

Data Index: 1241183 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 6.5484. Min Range: -6.5484

Max Act: 4.7905. Min Act: -0.0000

Data Index: 160058 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 6.5484. Min Range: -6.5484

Max Act: 4.6109. Min Act: -0.0000

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 6.5484. Min Range: -6.5484

Max Act: 4.6127. Min Act: -0.0000

Data Index: 740366 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 6.5484. Min Range: -6.5484

Max Act: 4.8660. Min Act: -0.0000

Data Index: 293616 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 6.5484. Min Range: -6.5484

Max Act: 4.5385. Min Act: -0.0000

Data Index: 725113 (C4 (Web Text))

Max Activating Token Index: 707