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

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

Neuron 2449 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2811. Min Act: -0.0000

Data Index: 463990 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1644. Min Act: -0.0000

Data Index: 46421 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2353. Min Act: -0.0000

Data Index: 773221 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2971. Min Act: -0.0000

Data Index: 298930 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1526. Min Act: -0.0000

Data Index: 216129 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9337. Min Act: -0.0000

Data Index: 235302 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0725. Min Act: -0.0000

Data Index: 395109 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0611. Min Act: -0.0000

Data Index: 537902 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0565. Min Act: -0.0000

Data Index: 271596 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2005. Min Act: -0.0000

Data Index: 851590 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0122. Min Act: -0.0000

Data Index: 381331 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0375. Min Act: -0.0000

Data Index: 441523 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0300. Min Act: -0.0000

Data Index: 494880 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1225279 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9200. Min Act: -0.0000

Data Index: 120889 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1037507 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1038215 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1442222 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1071596 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9349. Min Act: -0.0000

Data Index: 315653 (C4 (Web Text))

Max Activating Token Index: 512