Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1652 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0006

Data Index: 26253 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0731. Min Act: -0.0006

Data Index: 1112425 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0734. Min Act: -0.0005

Data Index: 444824 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0701. Min Act: -0.0006

Data Index: 48141 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0698. Min Act: -0.0006

Data Index: 1212164 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0692. Min Act: -0.0006

Data Index: 988863 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0685. Min Act: -0.0005

Data Index: 90273 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0720. Min Act: -0.0006

Data Index: 106076 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0665. Min Act: -0.0006

Data Index: 783152 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0681. Min Act: -0.0006

Data Index: 839641 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0650. Min Act: -0.0006

Data Index: 391404 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0678. Min Act: -0.0006

Data Index: 365651 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0663. Min Act: -0.0006

Data Index: 1020927 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0673. Min Act: -0.0006

Data Index: 334138 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0676. Min Act: -0.0005

Data Index: 413912 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0658. Min Act: -0.0006

Data Index: 1308979 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0652. Min Act: -0.0006

Data Index: 370395 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0649. Min Act: -0.0006

Data Index: 704472 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0649. Min Act: -0.0005

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0662. Min Act: -0.0006

Data Index: 1149338 (C4 (Web Text))

Max Activating Token Index: 574