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

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

Neuron 4286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0001

Data Index: 66472 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1016994 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0799. Min Act: -0.0001

Data Index: 420425 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0815. Min Act: -0.0001

Data Index: 535528 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1226360 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1127772 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0741. Min Act: -0.0001

Data Index: 662523 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0667. Min Act: -0.0001

Data Index: 93659 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0744. Min Act: -0.0001

Data Index: 267127 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0647. Min Act: -0.0001

Data Index: 271096 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0722. Min Act: -0.0001

Data Index: 512792 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0638. Min Act: -0.0001

Data Index: 443627 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0610. Min Act: -0.0001

Data Index: 440484 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0638. Min Act: -0.0001

Data Index: 531565 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0668. Min Act: -0.0001

Data Index: 637004 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0682. Min Act: -0.0001

Data Index: 770901 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0544. Min Act: -0.0001

Data Index: 534083 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0634. Min Act: -0.0001

Data Index: 547892 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0622. Min Act: -0.0001

Data Index: 49284 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0591. Min Act: -0.0001

Data Index: 212808 (C4 (Web Text))

Max Activating Token Index: 64