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

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

Neuron 3239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.7864. Min Act: -0.0000

Data Index: 42637 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 2.0092. Min Range: -2.0092

Max Act: 2.0092. Min Act: -0.0000

Data Index: 1143607 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.5564. Min Act: -0.0000

Data Index: 768403 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.7079. Min Act: -0.0000

Data Index: 622094 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.5777. Min Act: -0.0000

Data Index: 150141 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1311405 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.5812. Min Act: -0.0000

Data Index: 735599 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.4532. Min Act: -0.0000

Data Index: 147982 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.3829. Min Act: -0.0000

Data Index: 674341 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.5405. Min Act: -0.0000

Data Index: 11548 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.6448. Min Act: -0.0000

Data Index: 794392 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1074317 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.2728. Min Act: -0.0000

Data Index: 440231 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.4458. Min Act: -0.0000

Data Index: 70221 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1252224 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.2670. Min Act: -0.0000

Data Index: 674772 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.1992. Min Act: -0.0000

Data Index: 842504 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.2904. Min Act: -0.0000

Data Index: 729670 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.0873. Min Act: -0.0000

Data Index: 341232 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 2.0092. Min Range: -2.0092

Max Act: 1.2292. Min Act: -0.0000

Data Index: 1211548 (C4 (Web Text))

Max Activating Token Index: 861