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

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

Neuron 1614 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: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0002

Data Index: 124544 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0773. Min Act: -0.0002

Data Index: 618222 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1172622 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1245655 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0720. Min Act: -0.0002

Data Index: 667122 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0701. Min Act: -0.0002

Data Index: 563278 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0783. Min Act: -0.0002

Data Index: 501285 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0653. Min Act: -0.0002

Data Index: 621425 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0720. Min Act: -0.0002

Data Index: 273113 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0723. Min Act: -0.0002

Data Index: 234483 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1162929 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0720. Min Act: -0.0001

Data Index: 896731 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0699. Min Act: -0.0002

Data Index: 583706 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1165278 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1047187 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0698. Min Act: -0.0002

Data Index: 159695 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0686. Min Act: -0.0002

Data Index: 237816 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0659. Min Act: -0.0002

Data Index: 548977 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1190322 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0654. Min Act: -0.0002

Data Index: 492255 (C4 (Web Text))

Max Activating Token Index: 83