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

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

Neuron 432 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.1001. Min Act: -0.0006

Data Index: 18313 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0904. Min Act: -0.0006

Data Index: 838752 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0865. Min Act: -0.0006

Data Index: 723763 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0899. Min Act: -0.0006

Data Index: 905907 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0881. Min Act: -0.0006

Data Index: 738782 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0879. Min Act: -0.0006

Data Index: 926200 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0855. Min Act: -0.0006

Data Index: 685319 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0848. Min Act: -0.0006

Data Index: 355042 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0831. Min Act: -0.0006

Data Index: 576841 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0817. Min Act: -0.0006

Data Index: 637440 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0783. Min Act: -0.0006

Data Index: 1239298 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0777. Min Act: -0.0006

Data Index: 1321649 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0807. Min Act: -0.0006

Data Index: 773021 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0773. Min Act: -0.0006

Data Index: 864335 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0769. Min Act: -0.0006

Data Index: 995777 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0766. Min Act: -0.0006

Data Index: 447940 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0749. Min Act: -0.0006

Data Index: 485103 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0777. Min Act: -0.0006

Data Index: 253727 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0744. Min Act: -0.0006

Data Index: 437179 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0777. Min Act: -0.0006

Data Index: 40410 (C4 (Web Text))

Max Activating Token Index: 853