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

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

Neuron 1715 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: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 24257 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0650. Min Act: -0.0003

Data Index: 879670 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0601. Min Act: -0.0003

Data Index: 22551 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0575. Min Act: -0.0003

Data Index: 69279 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0569. Min Act: -0.0004

Data Index: 65909 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0572. Min Act: -0.0003

Data Index: 449576 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0586. Min Act: -0.0003

Data Index: 415189 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0551. Min Act: -0.0003

Data Index: 402954 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0550. Min Act: -0.0004

Data Index: 632316 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0558. Min Act: -0.0004

Data Index: 1185725 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0541. Min Act: -0.0003

Data Index: 381340 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1210628 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1161485 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0513. Min Act: -0.0003

Data Index: 634742 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0531. Min Act: -0.0003

Data Index: 438147 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0545. Min Act: -0.0004

Data Index: 753824 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1239478 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1088458 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0536. Min Act: -0.0003

Data Index: 674975 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1253867 (C4 (Web Text))

Max Activating Token Index: 162