Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1944 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.4037. Min Act: -0.0000

Data Index: 601651 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.0944. Min Act: -0.0000

Data Index: 1045992 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.7508. Min Act: -0.0000

Data Index: 1596956 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.5681. Min Act: -0.0000

Data Index: 1323535 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.3363. Min Act: -0.0000

Data Index: 446695 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.2491. Min Act: -0.0000

Data Index: 1781626 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.1317. Min Act: -0.0000

Data Index: 894230 (The Pile)

Max Activating Token Index: 147

Text #7

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.3625. Min Act: -0.0000

Data Index: 769683 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.3646. Min Act: -0.0000

Data Index: 1232766 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.2437. Min Act: -0.0000

Data Index: 1349493 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.3419. Min Act: -0.0000

Data Index: 993829 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0769. Min Act: -0.0000

Data Index: 1663591 (The Pile)

Max Activating Token Index: 828

Text #12

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1518391 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.2957. Min Act: -0.0000

Data Index: 697486 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.1476. Min Act: 0.0000

Data Index: 1510894 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.9211. Min Act: -0.0000

Data Index: 211778 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1696993 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0766. Min Act: -0.0000

Data Index: 754692 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0653. Min Act: -0.0000

Data Index: 1728308 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0718. Min Act: -0.0000

Data Index: 826533 (The Pile)

Max Activating Token Index: 138