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

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

Neuron 1390 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8226. Min Range: -4.8226

Max Act: 4.2238. Min Act: -0.0000

Data Index: 1536936 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 4.8226. Min Range: -4.8226

Max Act: 4.8226. Min Act: -0.0000

Data Index: 1527951 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.5699. Min Act: -0.0000

Data Index: 1384043 (Python Code)

Max Activating Token Index: 170

Text #3

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.4548. Min Act: -0.0000

Data Index: 1624760 (Python Code)

Max Activating Token Index: 909

Text #4

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.0230. Min Act: -0.0000

Data Index: 1408427 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.3445. Min Act: -0.0000

Data Index: 1560411 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.2162. Min Act: -0.0000

Data Index: 1614117 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.3427. Min Act: -0.0000

Data Index: 1523050 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.5111. Min Act: -0.0000

Data Index: 1558226 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.8847. Min Act: -0.0000

Data Index: 1437946 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.3119. Min Act: -0.0000

Data Index: 1410896 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.0556. Min Act: -0.0000

Data Index: 1447824 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.9355. Min Act: -0.0000

Data Index: 1623751 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.3066. Min Act: -0.0000

Data Index: 1463891 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 4.8226. Min Range: -4.8226

Max Act: 3.1525. Min Act: -0.0000

Data Index: 1420056 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.6686. Min Act: -0.0000

Data Index: 1417806 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.9345. Min Act: -0.0000

Data Index: 1593641 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.5240. Min Act: -0.0000

Data Index: 1378259 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.9214. Min Act: -0.0000

Data Index: 1623738 (Python Code)

Max Activating Token Index: 978

Text #19

Max Range: 4.8226. Min Range: -4.8226

Max Act: 2.3425. Min Act: -0.0000

Data Index: 1528397 (Python Code)

Max Activating Token Index: 935