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

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

Neuron 831 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1158091 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0737. Min Act: -0.0003

Data Index: 867983 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0726. Min Act: -0.0003

Data Index: 537478 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0721. Min Act: -0.0003

Data Index: 636366 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0701. Min Act: -0.0003

Data Index: 526143 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0667. Min Act: -0.0003

Data Index: 991618 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1134689 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0685. Min Act: -0.0003

Data Index: 93033 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0663. Min Act: -0.0003

Data Index: 445866 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0650. Min Act: -0.0003

Data Index: 266546 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0655. Min Act: -0.0003

Data Index: 157702 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0639. Min Act: -0.0003

Data Index: 236723 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0645. Min Act: -0.0003

Data Index: 907789 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0636. Min Act: -0.0003

Data Index: 382987 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0623. Min Act: -0.0003

Data Index: 797396 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0653. Min Act: -0.0003

Data Index: 562714 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0644. Min Act: -0.0003

Data Index: 347569 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0615. Min Act: -0.0003

Data Index: 686764 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0591. Min Act: -0.0003

Data Index: 695591 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0615. Min Act: -0.0003

Data Index: 481392 (C4 (Web Text))

Max Activating Token Index: 583