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

Dataset: The Pile

Neuron 79 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0778. Min Act: -0.0000

Data Index: 643328 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0000

Data Index: 821362 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0728. Min Act: -0.0000

Data Index: 489073 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1715374 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0704. Min Act: -0.0000

Data Index: 905627 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1467445 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0714. Min Act: -0.0000

Data Index: 972056 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0669. Min Act: 0.0000

Data Index: 352701 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0679. Min Act: -0.0000

Data Index: 286350 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0697. Min Act: 0.0000

Data Index: 1336515 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1648231 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1204685 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0641. Min Act: 0.0000

Data Index: 1369185 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0656. Min Act: -0.0000

Data Index: 579974 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1373151 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1842209 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1683132 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1322404 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0661. Min Act: 0.0000

Data Index: 1294831 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0634. Min Act: -0.0000

Data Index: 227075 (The Pile)

Max Activating Token Index: 283