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

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

Neuron 939 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: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0005

Data Index: 105304 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0463. Min Act: -0.0005

Data Index: 738798 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0497. Min Act: -0.0005

Data Index: 476722 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0481. Min Act: -0.0005

Data Index: 244573 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0488. Min Act: -0.0005

Data Index: 165494 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0421. Min Act: -0.0005

Data Index: 17735 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0427. Min Act: -0.0005

Data Index: 955447 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0419. Min Act: -0.0005

Data Index: 1344078 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0439. Min Act: -0.0005

Data Index: 533740 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0394. Min Act: -0.0005

Data Index: 527158 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0402. Min Act: -0.0005

Data Index: 478173 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0388. Min Act: -0.0005

Data Index: 622568 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0397. Min Act: -0.0005

Data Index: 520512 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0440. Min Act: -0.0005

Data Index: 799640 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0411. Min Act: -0.0005

Data Index: 828343 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1090848 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0400. Min Act: -0.0005

Data Index: 943772 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1215590 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0381. Min Act: -0.0005

Data Index: 463719 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0361. Min Act: -0.0005

Data Index: 167605 (C4 (Web Text))

Max Activating Token Index: 520