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

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

Neuron 2151 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: 0.2130. Min Range: -0.2130

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1570165 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1511917 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1631925 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1654280 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1606067 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1382073 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1490115 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1515180 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1469612 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1575231 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1607405 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1428559 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1332. Min Act: -0.0000

Data Index: 353856 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1372375 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1654543 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1600342 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1433295 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1572485 (Python Code)

Max Activating Token Index: 145

Text #18

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1580580 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1536745 (Python Code)

Max Activating Token Index: 164