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

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

Neuron 4322 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1527326 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1613703 (Python Code)

Max Activating Token Index: 646

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1420907 (Python Code)

Max Activating Token Index: 690

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1397921 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1474281 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1389494 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1374842 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1402155 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1466807 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1400052 (Python Code)

Max Activating Token Index: 809

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1389366 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1477355 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1608842 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1432972 (Python Code)

Max Activating Token Index: 784

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1561210 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1559307 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1585195 (Python Code)

Max Activating Token Index: 341

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1404927 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1443362 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1570527 (Python Code)

Max Activating Token Index: 689