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

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

Neuron 275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1523. Min Range: -2.1523

Max Act: 2.1523. Min Act: -0.0000

Data Index: 1586577 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.9135. Min Act: -0.0000

Data Index: 1374014 (Python Code)

Max Activating Token Index: 719

Text #2

Max Range: 2.1523. Min Range: -2.1523

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1520910 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.7890. Min Act: -0.0000

Data Index: 1454905 (Python Code)

Max Activating Token Index: 514

Text #4

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1522812 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.7668. Min Act: -0.0000

Data Index: 1558690 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.8558. Min Act: -0.0000

Data Index: 1527841 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.7581. Min Act: -0.0000

Data Index: 1465302 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.7656. Min Act: -0.0000

Data Index: 1604390 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1515532 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.8238. Min Act: -0.0000

Data Index: 1598716 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1536861 (Python Code)

Max Activating Token Index: 181

Text #12

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1401258 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5678. Min Act: -0.0000

Data Index: 1367157 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6660. Min Act: -0.0000

Data Index: 1584994 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1437123 (Python Code)

Max Activating Token Index: 644

Text #16

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1560580 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1566288 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5984. Min Act: -0.0000

Data Index: 1464585 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1473322 (Python Code)

Max Activating Token Index: 86