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

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

Neuron 2140 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: 1.7556. Min Range: -1.7556

Max Act: 1.7556. Min Act: -0.0000

Data Index: 1338721 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.7396. Min Act: -0.0000

Data Index: 342703 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1271459 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1488730 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1809. Min Act: 0.0000

Data Index: 190420 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1389849 (Python Code)

Max Activating Token Index: 1014

Text #6

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.3052. Min Act: -0.0000

Data Index: 84850 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1479482 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1593198 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1561427 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1823. Min Act: -0.0000

Data Index: 233716 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1756. Min Act: 0.0000

Data Index: 1226790 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1577655 (Python Code)

Max Activating Token Index: 994

Text #13

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.0685. Min Act: -0.0000

Data Index: 761680 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1283582 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.7556. Min Range: -1.7556

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1296877 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1504678 (Python Code)

Max Activating Token Index: 1002

Text #17

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.0996. Min Act: -0.0000

Data Index: 66196 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.1672. Min Act: -0.0000

Data Index: 593405 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.7556. Min Range: -1.7556

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1638506 (Python Code)

Max Activating Token Index: 219