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

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

Neuron 1770 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: 0.0573. Min Range: -0.0573

Max Act: 0.0563. Min Act: -0.0005

Data Index: 796953 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0572. Min Act: -0.0005

Data Index: 1214458 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0557. Min Act: -0.0005

Data Index: 423323 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0005

Data Index: 807432 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0550. Min Act: -0.0005

Data Index: 835522 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0523. Min Act: -0.0005

Data Index: 915063 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0504. Min Act: -0.0005

Data Index: 1211348 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0474. Min Act: -0.0005

Data Index: 56287 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0501. Min Act: -0.0005

Data Index: 898014 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0497. Min Act: -0.0005

Data Index: 310040 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0498. Min Act: -0.0005

Data Index: 174572 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0479. Min Act: -0.0005

Data Index: 223110 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0455. Min Act: -0.0005

Data Index: 904626 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0414. Min Act: -0.0005

Data Index: 310215 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0498. Min Act: -0.0005

Data Index: 654206 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0451. Min Act: -0.0005

Data Index: 438272 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0514. Min Act: -0.0005

Data Index: 1301296 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0417. Min Act: -0.0005

Data Index: 504294 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0446. Min Act: -0.0005

Data Index: 773893 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0464. Min Act: -0.0005

Data Index: 10369 (C4 (Web Text))

Max Activating Token Index: 724