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

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

Neuron 525 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: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0005

Data Index: 698021 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0449. Min Act: -0.0005

Data Index: 182099 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0447. Min Act: -0.0005

Data Index: 806578 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0425. Min Act: -0.0005

Data Index: 1358149 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0447. Min Act: -0.0005

Data Index: 648263 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0423. Min Act: -0.0005

Data Index: 306987 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0421. Min Act: -0.0005

Data Index: 907856 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0430. Min Act: -0.0005

Data Index: 166865 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1318449 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0425. Min Act: -0.0005

Data Index: 302564 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0409. Min Act: -0.0005

Data Index: 339395 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0005

Data Index: 721450 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0364. Min Act: -0.0005

Data Index: 255786 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0399. Min Act: -0.0005

Data Index: 913687 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0388. Min Act: -0.0005

Data Index: 867030 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0393. Min Act: -0.0005

Data Index: 167992 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0386. Min Act: -0.0005

Data Index: 495247 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0390. Min Act: -0.0005

Data Index: 189050 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0380. Min Act: -0.0005

Data Index: 238196 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0393. Min Act: -0.0005

Data Index: 837544 (C4 (Web Text))

Max Activating Token Index: 435