Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0000

Data Index: 22523 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1473472 (Python Code)

Max Activating Token Index: 376

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1596792 (Python Code)

Max Activating Token Index: 140

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1331755 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0536. Min Act: -0.0000

Data Index: 395399 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0476. Min Act: -0.0000

Data Index: 165585 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0395. Min Act: -0.0000

Data Index: 882191 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1369800 (Python Code)

Max Activating Token Index: 415

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0377. Min Act: -0.0000

Data Index: 589871 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1092362 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0364. Min Act: -0.0000

Data Index: 1349527 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1585676 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0380. Min Act: -0.0000

Data Index: 182061 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1485414 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0339. Min Act: -0.0000

Data Index: 388008 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0349. Min Act: -0.0000

Data Index: 962748 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0339. Min Act: -0.0000

Data Index: 602739 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1237808 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0344. Min Act: -0.0000

Data Index: 893059 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0359. Min Act: -0.0000

Data Index: 803725 (C4 (Web Text))

Max Activating Token Index: 371