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

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

Neuron 1110 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1575327 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1448066 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1540114 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1603115 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1515297 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1364166 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1586060 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1442743 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7467. Min Act: 0.0000

Data Index: 1491325 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1649227 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1442622 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1593937 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1599248 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1564766 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1594213 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1445976 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1532745 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1530543 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1605442 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 1.6324. Min Range: -1.6324

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1468749 (Python Code)

Max Activating Token Index: 609