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

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

Neuron 789 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: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0001

Data Index: 306260 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1120784 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0864. Min Act: -0.0002

Data Index: 613690 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1322793 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0838. Min Act: -0.0002

Data Index: 288078 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1820 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0846. Min Act: -0.0002

Data Index: 149973 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1041585 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0854. Min Act: -0.0002

Data Index: 809338 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0837. Min Act: -0.0002

Data Index: 736218 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0815. Min Act: -0.0002

Data Index: 848485 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0807. Min Act: 0.0002

Data Index: 795478 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0833. Min Act: -0.0002

Data Index: 2900 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1342174 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1183611 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0783. Min Act: -0.0002

Data Index: 342853 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0825. Min Act: -0.0002

Data Index: 680288 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0777. Min Act: -0.0002

Data Index: 553183 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0806. Min Act: -0.0002

Data Index: 30228 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0794. Min Act: -0.0002

Data Index: 443616 (C4 (Web Text))

Max Activating Token Index: 543