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

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

Neuron 956 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0005

Data Index: 822936 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0833. Min Act: -0.0005

Data Index: 945546 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0781. Min Act: -0.0005

Data Index: 615064 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0760. Min Act: -0.0005

Data Index: 326242 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0714. Min Act: -0.0005

Data Index: 625988 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0750. Min Act: -0.0005

Data Index: 159017 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0752. Min Act: -0.0005

Data Index: 56721 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0711. Min Act: -0.0005

Data Index: 411419 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0681. Min Act: -0.0005

Data Index: 323011 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0718. Min Act: -0.0005

Data Index: 797040 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0689. Min Act: -0.0005

Data Index: 194374 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0679. Min Act: -0.0005

Data Index: 291452 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0633. Min Act: -0.0005

Data Index: 614000 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0681. Min Act: -0.0005

Data Index: 614906 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0669. Min Act: -0.0005

Data Index: 508260 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0624. Min Act: -0.0005

Data Index: 381176 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0645. Min Act: -0.0005

Data Index: 1016331 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0651. Min Act: -0.0005

Data Index: 79757 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0654. Min Act: -0.0005

Data Index: 494392 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0657. Min Act: -0.0005

Data Index: 23586 (C4 (Web Text))

Max Activating Token Index: 29