Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 253 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0005

Data Index: 120071 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0726. Min Act: -0.0005

Data Index: 391837 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0728. Min Act: -0.0005

Data Index: 49268 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0724. Min Act: -0.0005

Data Index: 803114 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0683. Min Act: -0.0005

Data Index: 1057109 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0734. Min Act: -0.0005

Data Index: 562445 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0729. Min Act: -0.0005

Data Index: 1174651 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0714. Min Act: -0.0005

Data Index: 656353 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0689. Min Act: -0.0005

Data Index: 315921 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0712. Min Act: -0.0005

Data Index: 327411 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0703. Min Act: -0.0005

Data Index: 824166 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0653. Min Act: -0.0005

Data Index: 930083 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0711. Min Act: -0.0005

Data Index: 268458 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0631. Min Act: -0.0005

Data Index: 289706 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0678. Min Act: -0.0005

Data Index: 358444 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0723. Min Act: -0.0005

Data Index: 753624 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0694. Min Act: -0.0005

Data Index: 100862 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0648. Min Act: -0.0005

Data Index: 893475 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0659. Min Act: -0.0005

Data Index: 245338 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0676. Min Act: -0.0005

Data Index: 582053 (C4 (Web Text))

Max Activating Token Index: 506