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

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

Neuron 1503 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: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0002

Data Index: 114745 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0892. Min Act: -0.0002

Data Index: 979684 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1020911 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0829. Min Act: -0.0002

Data Index: 926566 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0788. Min Act: -0.0002

Data Index: 804381 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0753. Min Act: -0.0002

Data Index: 875051 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0762. Min Act: -0.0002

Data Index: 55533 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1014117 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1149415 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1077287 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0758. Min Act: -0.0002

Data Index: 840805 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0744. Min Act: -0.0002

Data Index: 884402 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1208141 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0796. Min Act: -0.0002

Data Index: 767947 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0752. Min Act: -0.0002

Data Index: 78617 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0754. Min Act: -0.0002

Data Index: 113374 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1246727 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0731. Min Act: -0.0002

Data Index: 778945 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0742. Min Act: -0.0002

Data Index: 885250 (C4 (Web Text))

Max Activating Token Index: 780