Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 21 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0821. Min Act: -0.0003

Data Index: 195092 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0801. Min Act: -0.0003

Data Index: 919896 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0003

Data Index: 984386 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0741. Min Act: -0.0003

Data Index: 197892 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1326565 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1016099 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1157140 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0663. Min Act: -0.0003

Data Index: 998607 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0645. Min Act: -0.0003

Data Index: 456472 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0683. Min Act: -0.0003

Data Index: 192950 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1263886 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0604. Min Act: -0.0003

Data Index: 607037 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0667. Min Act: -0.0003

Data Index: 126473 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0655. Min Act: -0.0003

Data Index: 381581 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0560. Min Act: -0.0003

Data Index: 153337 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0664. Min Act: -0.0003

Data Index: 821604 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0598. Min Act: -0.0003

Data Index: 621576 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0591. Min Act: -0.0003

Data Index: 616653 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0631. Min Act: -0.0003

Data Index: 313017 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1303884 (C4 (Web Text))

Max Activating Token Index: 964