Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4728 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0314. Min Range: -6.0314

Max Act: 6.0314. Min Act: -0.0000

Data Index: 1560136 (Python Code)

Max Activating Token Index: 403

Text #1

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.5773. Min Act: -0.0000

Data Index: 1457048 (Python Code)

Max Activating Token Index: 970

Text #2

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.2187. Min Act: -0.0000

Data Index: 1519323 (Python Code)

Max Activating Token Index: 875

Text #3

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.9679. Min Act: -0.0000

Data Index: 1400740 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.1670. Min Act: -0.0000

Data Index: 1543897 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.7506. Min Act: -0.0000

Data Index: 1412808 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.7674. Min Act: -0.0000

Data Index: 1654830 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.1177. Min Act: -0.0000

Data Index: 1557034 (Python Code)

Max Activating Token Index: 823

Text #8

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.1346. Min Act: -0.0000

Data Index: 1376406 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.7076. Min Act: -0.0000

Data Index: 1534731 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.6775. Min Act: -0.0000

Data Index: 1414786 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.6326. Min Act: -0.0000

Data Index: 1557078 (Python Code)

Max Activating Token Index: 831

Text #12

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.6430. Min Act: -0.0000

Data Index: 1497267 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.2926. Min Act: -0.0000

Data Index: 1609716 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.4404. Min Act: -0.0000

Data Index: 1368986 (Python Code)

Max Activating Token Index: 299

Text #15

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.5651. Min Act: -0.0000

Data Index: 1590953 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.3905. Min Act: -0.0000

Data Index: 1390506 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.5690. Min Act: -0.0000

Data Index: 1613099 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.5557. Min Act: -0.0000

Data Index: 1567185 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 6.0314. Min Range: -6.0314

Max Act: 4.5312. Min Act: -0.0000

Data Index: 1419944 (Python Code)

Max Activating Token Index: 787