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

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

Neuron 285 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.3468. Min Act: -0.0000

Data Index: 987167 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.2004. Min Act: -0.0000

Data Index: 530370 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1829. Min Act: -0.0000

Data Index: 884925 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1985. Min Act: -0.0000

Data Index: 583785 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1283. Min Act: -0.0000

Data Index: 502267 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1079009 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1378. Min Act: -0.0000

Data Index: 23192 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1319. Min Act: -0.0000

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0633. Min Act: -0.0000

Data Index: 211911 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1137. Min Act: -0.0000

Data Index: 901009 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0189. Min Act: -0.0000

Data Index: 902177 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0650. Min Act: -0.0000

Data Index: 870659 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0606. Min Act: -0.0000

Data Index: 81169 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0242. Min Act: -0.0000

Data Index: 502745 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1544887 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0264. Min Act: -0.0000

Data Index: 80013 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0334. Min Act: -0.0000

Data Index: 16151 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0268. Min Act: -0.0000

Data Index: 9304 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0019. Min Act: -0.0000

Data Index: 52240 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0225. Min Act: -0.0000

Data Index: 81749 (C4 (Web Text))

Max Activating Token Index: 179