Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 588 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1111. Min Act: -0.0001

Data Index: 981033 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1560406 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1143847 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0969. Min Act: -0.0001

Data Index: 621960 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1554330 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1600367 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1384917 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0860. Min Act: -0.0001

Data Index: 422900 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0818. Min Act: -0.0001

Data Index: 786090 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0835. Min Act: -0.0001

Data Index: 299653 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1593947 (Python Code)

Max Activating Token Index: 760

Text #11

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0762. Min Act: -0.0001

Data Index: 455622 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1038827 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1268937 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0772. Min Act: -0.0001

Data Index: 226353 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1412350 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0761. Min Act: -0.0001

Data Index: 601977 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1003344 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0798. Min Act: -0.0001

Data Index: 11114 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0749. Min Act: -0.0001

Data Index: 726825 (C4 (Web Text))

Max Activating Token Index: 82