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

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

Neuron 1257 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: 0.0857. Min Range: -0.0857

Max Act: 0.0857. Min Act: -0.0002

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0739. Min Act: -0.0002

Data Index: 236140 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0738. Min Act: -0.0002

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1170456 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0704. Min Act: -0.0002

Data Index: 335739 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1178305 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0718. Min Act: -0.0002

Data Index: 128239 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0722. Min Act: -0.0002

Data Index: 961903 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0643. Min Act: -0.0002

Data Index: 759305 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1166246 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0682. Min Act: -0.0003

Data Index: 37198 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0682. Min Act: -0.0003

Data Index: 716965 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0705. Min Act: -0.0003

Data Index: 791945 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1047014 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0716. Min Act: -0.0002

Data Index: 659381 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0729. Min Act: -0.0002

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0669. Min Act: -0.0002

Data Index: 790054 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1076770 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0701. Min Act: -0.0002

Data Index: 901300 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0660. Min Act: -0.0002

Data Index: 313174 (C4 (Web Text))

Max Activating Token Index: 599