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

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

Neuron 2037 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: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0003

Data Index: 622253 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0564. Min Act: -0.0003

Data Index: 586597 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0551. Min Act: -0.0003

Data Index: 421994 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0549. Min Act: -0.0003

Data Index: 763035 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0538. Min Act: -0.0003

Data Index: 394163 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0531. Min Act: -0.0003

Data Index: 411238 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1112102 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1114655 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0522. Min Act: -0.0003

Data Index: 138149 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0533. Min Act: -0.0003

Data Index: 608674 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0530. Min Act: -0.0003

Data Index: 901220 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0515. Min Act: -0.0003

Data Index: 464962 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0519. Min Act: -0.0003

Data Index: 666505 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0505. Min Act: -0.0004

Data Index: 1160820 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0534. Min Act: -0.0003

Data Index: 652103 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0525. Min Act: -0.0003

Data Index: 716982 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0516. Min Act: -0.0003

Data Index: 979510 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0506. Min Act: -0.0003

Data Index: 339786 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0528. Min Act: -0.0004

Data Index: 1239384 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0531. Min Act: -0.0003

Data Index: 569393 (C4 (Web Text))

Max Activating Token Index: 649