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

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

Neuron 4472 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1471554 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0002

Data Index: 151448 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1387377 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1554848 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1517598 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1644441 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0395. Min Act: -0.0002

Data Index: 864155 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1429435 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1178561 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1589081 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0418. Min Act: -0.0002

Data Index: 376474 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1571744 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1572762 (Python Code)

Max Activating Token Index: 358

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0345. Min Act: -0.0002

Data Index: 730222 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0377. Min Act: -0.0002

Data Index: 156639 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1060835 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0367. Min Act: -0.0002

Data Index: 901225 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1445489 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0368. Min Act: -0.0002

Data Index: 690094 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1492262 (Python Code)

Max Activating Token Index: 51