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

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

Neuron 3569 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7996. Min Range: -2.7996

Max Act: 2.7996. Min Act: -0.0000

Data Index: 1451294 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 2.7996. Min Range: -2.7996

Max Act: 2.0684. Min Act: -0.0000

Data Index: 1374849 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 2.7996. Min Range: -2.7996

Max Act: 2.0725. Min Act: -0.0000

Data Index: 1617220 (Python Code)

Max Activating Token Index: 494

Text #3

Max Range: 2.7996. Min Range: -2.7996

Max Act: 2.0689. Min Act: -0.0000

Data Index: 1500460 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.9810. Min Act: -0.0000

Data Index: 1604290 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.8773. Min Act: -0.0000

Data Index: 1506179 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 2.7996. Min Range: -2.7996

Max Act: 2.0941. Min Act: -0.0000

Data Index: 1473481 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.7386. Min Act: -0.0000

Data Index: 1593453 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.8961. Min Act: -0.0000

Data Index: 1464384 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.8770. Min Act: -0.0000

Data Index: 1097106 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.6524. Min Act: -0.0000

Data Index: 487377 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.8178. Min Act: -0.0000

Data Index: 324766 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1556026 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.7489. Min Act: -0.0000

Data Index: 1378975 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.6533. Min Act: -0.0000

Data Index: 1251505 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.6191. Min Act: -0.0000

Data Index: 302908 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.4850. Min Act: -0.0000

Data Index: 868666 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1032908 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.5719. Min Act: -0.0000

Data Index: 373401 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.7996. Min Range: -2.7996

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 24