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

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

Neuron 1154 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: 0.7373. Min Range: -0.7373

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1544316 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1503516 (Python Code)

Max Activating Token Index: 863

Text #2

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1385621 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1590859 (Python Code)

Max Activating Token Index: 533

Text #4

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1418401 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1498911 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1566163 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1422214 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1409951 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1409938 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1394706 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1518813 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1635724 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1551660 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1379531 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1416401 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1647265 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1585220 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1377618 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1404366 (Python Code)

Max Activating Token Index: 224