Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0002

Data Index: 480290 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0727. Min Act: -0.0002

Data Index: 738526 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0723. Min Act: -0.0002

Data Index: 797306 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0678. Min Act: -0.0002

Data Index: 495654 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0673. Min Act: -0.0002

Data Index: 946277 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1124594 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1103158 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0633. Min Act: -0.0002

Data Index: 992596 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1120780 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0644. Min Act: -0.0002

Data Index: 463616 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0662. Min Act: -0.0002

Data Index: 700386 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0612. Min Act: -0.0002

Data Index: 598134 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1167020 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0612. Min Act: -0.0002

Data Index: 515424 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0612. Min Act: -0.0002

Data Index: 211371 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1288783 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0626. Min Act: -0.0002

Data Index: 578323 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0597. Min Act: -0.0002

Data Index: 868869 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0002

Data Index: 943982 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1356500 (C4 (Web Text))

Max Activating Token Index: 316