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

Dataset: The Pile

Neuron 4172 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: 0.4404. Min Range: -0.4404

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1170892 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2721. Min Act: -0.0000

Data Index: 128274 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2693. Min Act: -0.0000

Data Index: 497292 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2865. Min Act: -0.0000

Data Index: 590760 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2889. Min Act: -0.0000

Data Index: 763854 (The Pile)

Max Activating Token Index: 863

Text #5

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1571434 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2944. Min Act: -0.0000

Data Index: 258079 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2720. Min Act: -0.0000

Data Index: 678393 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1156986 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1201176 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2579. Min Act: -0.0000

Data Index: 220619 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2640. Min Act: -0.0000

Data Index: 597719 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2617. Min Act: -0.0000

Data Index: 86062 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2471. Min Act: -0.0000

Data Index: 472730 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2516. Min Act: -0.0000

Data Index: 864778 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2678. Min Act: -0.0000

Data Index: 118204 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2438. Min Act: -0.0000

Data Index: 433063 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1336043 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2548. Min Act: -0.0000

Data Index: 282601 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2541. Min Act: -0.0000

Data Index: 120354 (The Pile)

Max Activating Token Index: 293