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

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

Neuron 2165 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1566966 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0523. Min Act: -0.0003

Data Index: 706866 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1070913 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0468. Min Act: -0.0002

Data Index: 964506 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1462879 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0436. Min Act: -0.0002

Data Index: 955496 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0433. Min Act: -0.0002

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1239838 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0408. Min Act: -0.0003

Data Index: 254781 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0415. Min Act: -0.0002

Data Index: 555695 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1372895 (Python Code)

Max Activating Token Index: 819

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0400. Min Act: -0.0003

Data Index: 105374 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1096627 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1146158 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0393. Min Act: -0.0003

Data Index: 64491 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0388. Min Act: -0.0003

Data Index: 143393 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0395. Min Act: -0.0003

Data Index: 325542 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1362361 (Python Code)

Max Activating Token Index: 891

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0383. Min Act: -0.0003

Data Index: 247270 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0359. Min Act: -0.0003

Data Index: 80912 (C4 (Web Text))

Max Activating Token Index: 196