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

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

Neuron 651 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: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0006

Data Index: 323127 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0807. Min Act: -0.0006

Data Index: 1338010 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0771. Min Act: -0.0006

Data Index: 141136 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0808. Min Act: -0.0006

Data Index: 1313639 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0768. Min Act: -0.0006

Data Index: 131830 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0762. Min Act: -0.0006

Data Index: 889232 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0757. Min Act: -0.0006

Data Index: 921908 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0754. Min Act: -0.0006

Data Index: 815051 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0736. Min Act: -0.0006

Data Index: 148592 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0749. Min Act: -0.0006

Data Index: 341891 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0746. Min Act: -0.0006

Data Index: 482001 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0745. Min Act: -0.0006

Data Index: 661214 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0727. Min Act: -0.0006

Data Index: 1142302 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0754. Min Act: -0.0006

Data Index: 952427 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0772. Min Act: -0.0006

Data Index: 241651 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0737. Min Act: -0.0006

Data Index: 853101 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0750. Min Act: -0.0006

Data Index: 1252987 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0728. Min Act: -0.0006

Data Index: 1292600 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0714. Min Act: -0.0006

Data Index: 250340 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0743. Min Act: -0.0006

Data Index: 681979 (C4 (Web Text))

Max Activating Token Index: 262