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

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

Neuron 2602 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: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1469729 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1505946 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1118649 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0448. Min Act: -0.0001

Data Index: 53564 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0393. Min Act: -0.0001

Data Index: 491211 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0420. Min Act: -0.0001

Data Index: 157923 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0453. Min Act: -0.0001

Data Index: 302929 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0394. Min Act: -0.0001

Data Index: 50030 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0366. Min Act: -0.0001

Data Index: 794650 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0336. Min Act: -0.0001

Data Index: 476079 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0444. Min Act: -0.0001

Data Index: 57255 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1574437 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0389. Min Act: -0.0001

Data Index: 712976 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1374532 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0333. Min Act: -0.0001

Data Index: 308355 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0381. Min Act: -0.0001

Data Index: 734901 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1509087 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1467341 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0372. Min Act: -0.0001

Data Index: 638328 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0346. Min Act: -0.0001

Data Index: 398861 (C4 (Web Text))

Max Activating Token Index: 686