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

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

Neuron 4592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0002

Data Index: 490412 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1134438 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1004103 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0873. Min Act: -0.0002

Data Index: 398730 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0782. Min Act: -0.0002

Data Index: 759837 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1249622 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0839. Min Act: -0.0002

Data Index: 264742 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0770. Min Act: -0.0002

Data Index: 963299 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0766. Min Act: -0.0002

Data Index: 62548 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0753. Min Act: -0.0002

Data Index: 862324 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0744. Min Act: -0.0002

Data Index: 318246 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1324106 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1214199 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0730. Min Act: -0.0002

Data Index: 374928 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1252876 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0753. Min Act: -0.0002

Data Index: 669169 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0741. Min Act: -0.0002

Data Index: 822120 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0728. Min Act: -0.0002

Data Index: 623329 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0766. Min Act: -0.0002

Data Index: 260711 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0694. Min Act: -0.0002

Data Index: 584985 (C4 (Web Text))

Max Activating Token Index: 68