Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.1050. Min Act: -0.0002

Data Index: 230904 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.1013. Min Act: -0.0002

Data Index: 372177 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0935. Min Act: -0.0002

Data Index: 131091 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0856. Min Act: -0.0002

Data Index: 770003 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0912. Min Act: -0.0002

Data Index: 725234 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0864. Min Act: -0.0002

Data Index: 511885 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1408828 (Python Code)

Max Activating Token Index: 505

Text #7

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0831. Min Act: -0.0002

Data Index: 337636 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0829. Min Act: -0.0002

Data Index: 897453 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0834. Min Act: -0.0002

Data Index: 882867 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0805. Min Act: -0.0002

Data Index: 229483 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0765. Min Act: -0.0002

Data Index: 631745 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1341469 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0810. Min Act: -0.0002

Data Index: 292290 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1381556 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0745. Min Act: -0.0002

Data Index: 279783 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1074566 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1370133 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1000752 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0778. Min Act: -0.0002

Data Index: 749207 (C4 (Web Text))

Max Activating Token Index: 670