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

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

Neuron 3662 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1307. Min Range: -2.1307

Max Act: 2.1307. Min Act: -0.0000

Data Index: 1443357 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 2.1307. Min Range: -2.1307

Max Act: 2.0789. Min Act: -0.0000

Data Index: 1383389 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1488230 (Python Code)

Max Activating Token Index: 564

Text #3

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1497373 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.7349. Min Act: -0.0000

Data Index: 1511657 (Python Code)

Max Activating Token Index: 724

Text #5

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.6586. Min Act: -0.0000

Data Index: 1545845 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1432931 (Python Code)

Max Activating Token Index: 320

Text #7

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.7605. Min Act: -0.0000

Data Index: 1587438 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.6562. Min Act: -0.0000

Data Index: 1555805 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.5642. Min Act: -0.0000

Data Index: 1499054 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.4668. Min Act: -0.0000

Data Index: 1439379 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.6258. Min Act: -0.0000

Data Index: 1638982 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.8030. Min Act: -0.0000

Data Index: 1525187 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1389706 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1611582 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1420891 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1591684 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1549279 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1419995 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 2.1307. Min Range: -2.1307

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1617402 (Python Code)

Max Activating Token Index: 7