Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2610 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0000

Data Index: 773400 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0523. Min Act: -0.0000

Data Index: 982573 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0536. Min Act: -0.0001

Data Index: 978070 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0488. Min Act: -0.0000

Data Index: 774349 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0479. Min Act: -0.0001

Data Index: 606068 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1048877 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0428. Min Act: -0.0001

Data Index: 654663 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0458. Min Act: -0.0001

Data Index: 533202 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0429. Min Act: -0.0000

Data Index: 857009 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0437. Min Act: -0.0000

Data Index: 194948 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0415. Min Act: -0.0001

Data Index: 842874 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1015499 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0434. Min Act: -0.0001

Data Index: 569643 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0411. Min Act: -0.0001

Data Index: 621962 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1039791 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0446. Min Act: -0.0001

Data Index: 822021 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0419. Min Act: -0.0000

Data Index: 558618 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0388. Min Act: -0.0001

Data Index: 425015 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0397. Min Act: -0.0000

Data Index: 62182 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0386. Min Act: -0.0000

Data Index: 242718 (C4 (Web Text))

Max Activating Token Index: 195