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

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

Neuron 1616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0002

Data Index: 157140 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0588. Min Act: -0.0002

Data Index: 522626 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1133696 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1249611 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0515. Min Act: -0.0002

Data Index: 245182 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0597. Min Act: -0.0002

Data Index: 379063 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1186826 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0524. Min Act: -0.0002

Data Index: 743300 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0577. Min Act: -0.0002

Data Index: 695645 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0460. Min Act: -0.0002

Data Index: 565764 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0569. Min Act: -0.0002

Data Index: 913306 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1333022 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0452. Min Act: -0.0002

Data Index: 394660 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0577. Min Act: -0.0002

Data Index: 528195 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0494. Min Act: -0.0002

Data Index: 859521 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0492. Min Act: -0.0002

Data Index: 919786 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0475. Min Act: -0.0002

Data Index: 835379 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0454. Min Act: -0.0002

Data Index: 905959 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1217619 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0455. Min Act: -0.0002

Data Index: 798346 (C4 (Web Text))

Max Activating Token Index: 165