Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 18 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1016345 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1039561 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1312183 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0552. Min Act: -0.0003

Data Index: 465432 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0558. Min Act: -0.0002

Data Index: 619096 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0553. Min Act: -0.0003

Data Index: 586476 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0556. Min Act: -0.0002

Data Index: 178965 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0556. Min Act: -0.0003

Data Index: 881484 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0536. Min Act: -0.0002

Data Index: 707720 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0528. Min Act: -0.0003

Data Index: 530112 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0518. Min Act: -0.0003

Data Index: 742571 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0508. Min Act: -0.0002

Data Index: 341732 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0501. Min Act: -0.0003

Data Index: 413620 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1342683 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0506. Min Act: -0.0003

Data Index: 569653 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1024664 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0499. Min Act: -0.0003

Data Index: 60376 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1197355 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0498. Min Act: -0.0003

Data Index: 973606 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0469. Min Act: -0.0003

Data Index: 190609 (C4 (Web Text))

Max Activating Token Index: 621