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

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

Neuron 664 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1447961 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1536805 (Python Code)

Max Activating Token Index: 765

Text #2

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1365102 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1651256 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1562397 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1486612 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1656307 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1446745 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1559980 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1452110 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1652820 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1462876 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1545915 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1483751 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1609870 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1371172 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1475277 (Python Code)

Max Activating Token Index: 631

Text #17

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1608648 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1599354 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1380896 (Python Code)

Max Activating Token Index: 338