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

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

Neuron 1374 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1446034 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.3265. Min Act: -0.0000

Data Index: 1432695 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.2119. Min Act: -0.0000

Data Index: 1572532 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.0992. Min Act: -0.0000

Data Index: 1475538 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.0815. Min Act: -0.0000

Data Index: 1506436 (Python Code)

Max Activating Token Index: 636

Text #5

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.2072. Min Act: -0.0000

Data Index: 1411234 (Python Code)

Max Activating Token Index: 418

Text #6

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1649435 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.1173. Min Act: -0.0000

Data Index: 286272 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1433422 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.2135. Min Act: -0.0000

Data Index: 1507224 (Python Code)

Max Activating Token Index: 342

Text #10

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.1909. Min Act: -0.0000

Data Index: 1614510 (Python Code)

Max Activating Token Index: 433

Text #11

Max Range: 2.3265. Min Range: -2.3265

Max Act: 2.1587. Min Act: -0.0000

Data Index: 1408540 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.9919. Min Act: -0.0000

Data Index: 1634871 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.9384. Min Act: -0.0000

Data Index: 1636615 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.7073. Min Act: -0.0000

Data Index: 490645 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.7646. Min Act: -0.0000

Data Index: 1517814 (Python Code)

Max Activating Token Index: 1002

Text #16

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1396203 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1531256 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.7396. Min Act: -0.0000

Data Index: 1486369 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 2.3265. Min Range: -2.3265

Max Act: 1.7504. Min Act: -0.0000

Data Index: 490854 (C4 (Web Text))

Max Activating Token Index: 453