Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1055 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8703. Min Act: -0.0001

Data Index: 1144973 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8001. Min Act: -0.0001

Data Index: 551851 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1222437 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1175145 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7245. Min Act: -0.0001

Data Index: 489686 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7736. Min Act: -0.0001

Data Index: 1288622 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7165. Min Act: -0.0001

Data Index: 872221 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6279. Min Act: -0.0001

Data Index: 1007623 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6861. Min Act: -0.0001

Data Index: 241141 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6907. Min Act: -0.0001

Data Index: 376760 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6775. Min Act: -0.0001

Data Index: 546774 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7238. Min Act: -0.0001

Data Index: 140300 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6805. Min Act: -0.0001

Data Index: 496472 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6512. Min Act: -0.0001

Data Index: 120317 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6704. Min Act: -0.0001

Data Index: 1229538 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6675. Min Act: -0.0001

Data Index: 690397 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1284261 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6823. Min Act: -0.0001

Data Index: 907817 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6932. Min Act: -0.0001

Data Index: 1141951 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6601. Min Act: -0.0001

Data Index: 984977 (C4 (Web Text))

Max Activating Token Index: 507