Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1207 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.4256. Min Range: -4.4256

Max Act: 4.0003. Min Act: -0.0001

Data Index: 1443182 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 4.4256. Min Range: -4.4256

Max Act: 4.0293. Min Act: -0.0001

Data Index: 1513586 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 4.4256. Min Range: -4.4256

Max Act: 4.4256. Min Act: -0.0001

Data Index: 1469864 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.9077. Min Act: -0.0001

Data Index: 1447493 (Python Code)

Max Activating Token Index: 433

Text #4

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.5692. Min Act: -0.0000

Data Index: 1583233 (Python Code)

Max Activating Token Index: 497

Text #5

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.6029. Min Act: -0.0001

Data Index: 1520826 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.6560. Min Act: -0.0000

Data Index: 1451405 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.2174. Min Act: -0.0001

Data Index: 1557130 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.1650. Min Act: -0.0000

Data Index: 1486464 (Python Code)

Max Activating Token Index: 721

Text #9

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.9546. Min Act: -0.0001

Data Index: 1578836 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.6845. Min Act: -0.0001

Data Index: 1455513 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.5560. Min Act: -0.0001

Data Index: 1360250 (Python Code)

Max Activating Token Index: 235

Text #12

Max Range: 4.4256. Min Range: -4.4256

Max Act: 3.0719. Min Act: -0.0001

Data Index: 1606638 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.7441. Min Act: -0.0000

Data Index: 1564482 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.7592. Min Act: -0.0001

Data Index: 1594407 (Python Code)

Max Activating Token Index: 596

Text #15

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.7436. Min Act: -0.0000

Data Index: 1520832 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.7666. Min Act: -0.0000

Data Index: 1391211 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.6285. Min Act: -0.0000

Data Index: 1499501 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.6754. Min Act: -0.0000

Data Index: 1465824 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 4.4256. Min Range: -4.4256

Max Act: 2.5525. Min Act: -0.0000

Data Index: 1469773 (Python Code)

Max Activating Token Index: 103