Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0002

Data Index: 938007 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1046703 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1238438 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1120163 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0655. Min Act: -0.0002

Data Index: 376393 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0668. Min Act: -0.0002

Data Index: 607960 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0614. Min Act: -0.0002

Data Index: 553380 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1064708 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0601. Min Act: -0.0002

Data Index: 645267 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0594. Min Act: -0.0002

Data Index: 741532 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0595. Min Act: -0.0002

Data Index: 809672 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0595. Min Act: -0.0002

Data Index: 753379 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0588. Min Act: -0.0002

Data Index: 17358 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1355501 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0535. Min Act: -0.0002

Data Index: 857614 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0555. Min Act: -0.0002

Data Index: 22710 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1122895 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1078779 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0540. Min Act: -0.0002

Data Index: 582645 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0566. Min Act: -0.0002

Data Index: 425319 (C4 (Web Text))

Max Activating Token Index: 314