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

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

Neuron 1780 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: 0.0792. Min Range: -0.0792

Max Act: 0.0766. Min Act: -0.0001

Data Index: 945678 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0002

Data Index: 483385 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1324920 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0748. Min Act: -0.0001

Data Index: 794250 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1041896 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0707. Min Act: -0.0001

Data Index: 60221 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0709. Min Act: -0.0001

Data Index: 55521 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1119923 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0717. Min Act: -0.0002

Data Index: 118789 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0694. Min Act: -0.0000

Data Index: 559987 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0703. Min Act: -0.0002

Data Index: 667112 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0685. Min Act: -0.0002

Data Index: 106726 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0676. Min Act: -0.0001

Data Index: 565687 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1298218 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0663. Min Act: -0.0002

Data Index: 970483 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1214456 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0683. Min Act: -0.0001

Data Index: 720742 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0679. Min Act: -0.0002

Data Index: 772265 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0665. Min Act: -0.0002

Data Index: 485541 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0666. Min Act: -0.0002

Data Index: 262224 (C4 (Web Text))

Max Activating Token Index: 657