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

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

Neuron 3764 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0558. Min Act: -0.0001

Data Index: 306324 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0001

Data Index: 643976 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0560. Min Act: -0.0001

Data Index: 413727 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1041820 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0509. Min Act: -0.0001

Data Index: 717815 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0566. Min Act: -0.0002

Data Index: 518763 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1148703 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0533. Min Act: -0.0002

Data Index: 360037 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0508. Min Act: -0.0002

Data Index: 555680 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0535. Min Act: -0.0002

Data Index: 654268 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0484. Min Act: -0.0001

Data Index: 671601 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0001

Data Index: 412681 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0501. Min Act: -0.0001

Data Index: 367265 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1048797 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0515. Min Act: -0.0002

Data Index: 850764 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0509. Min Act: -0.0002

Data Index: 339107 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1168895 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0452. Min Act: -0.0002

Data Index: 33551 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0473. Min Act: -0.0002

Data Index: 211504 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0470. Min Act: -0.0002

Data Index: 362520 (C4 (Web Text))

Max Activating Token Index: 906