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

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

Neuron 3408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.7603. Min Act: -0.0000

Data Index: 555190 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.1741. Min Act: -0.0000

Data Index: 292056 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.1957. Min Act: -0.0000

Data Index: 472605 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.2843. Min Act: -0.0000

Data Index: 614289 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.9020. Min Act: -0.0000

Data Index: 985000 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.0669. Min Act: -0.0000

Data Index: 874537 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.0922. Min Act: -0.0000

Data Index: 929869 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.0550. Min Act: -0.0000

Data Index: 754059 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.0833. Min Act: -0.0000

Data Index: 794269 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.8379. Min Act: -0.0000

Data Index: 458263 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 2.7603. Min Range: -2.7603

Max Act: 2.0493. Min Act: -0.0000

Data Index: 84683 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.8482. Min Act: -0.0000

Data Index: 533238 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.7983. Min Act: -0.0000

Data Index: 220597 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.8791. Min Act: -0.0000

Data Index: 1118290 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.7834. Min Act: -0.0000

Data Index: 916516 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.5700. Min Act: -0.0000

Data Index: 158804 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1295764 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1238516 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.6324. Min Act: -0.0000

Data Index: 382551 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 2.7603. Min Range: -2.7603

Max Act: 1.8410. Min Act: -0.0000

Data Index: 658280 (C4 (Web Text))

Max Activating Token Index: 783