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

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

Neuron 5896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0002

Data Index: 212960 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1019138 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0887. Min Act: -0.0002

Data Index: 718346 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0877. Min Act: -0.0002

Data Index: 349186 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0831. Min Act: -0.0002

Data Index: 551448 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1100444 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0792. Min Act: -0.0002

Data Index: 295457 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0789. Min Act: -0.0002

Data Index: 901101 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1140742 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1353716 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0730. Min Act: -0.0002

Data Index: 92363 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0747. Min Act: -0.0002

Data Index: 702094 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1524418 (Python Code)

Max Activating Token Index: 549

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1069998 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0695. Min Act: -0.0002

Data Index: 269212 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0685. Min Act: -0.0002

Data Index: 993095 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0653. Min Act: -0.0002

Data Index: 17189 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0676. Min Act: -0.0002

Data Index: 460664 (C4 (Web Text))

Max Activating Token Index: 86