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

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

Neuron 4365 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.9284. Min Act: -0.0002

Data Index: 1620665 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8281. Min Act: -0.0002

Data Index: 1360274 (Python Code)

Max Activating Token Index: 637

Text #2

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8538. Min Act: -0.0002

Data Index: 1401808 (Python Code)

Max Activating Token Index: 454

Text #3

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7813. Min Act: -0.0002

Data Index: 1437602 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8063. Min Act: -0.0002

Data Index: 1461250 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8384. Min Act: -0.0002

Data Index: 1387924 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7834. Min Act: -0.0002

Data Index: 1466428 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8256. Min Act: -0.0002

Data Index: 1599084 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8002. Min Act: -0.0002

Data Index: 1579623 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8490. Min Act: -0.0002

Data Index: 1462320 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7733. Min Act: -0.0002

Data Index: 1588804 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7944. Min Act: -0.0002

Data Index: 1474357 (Python Code)

Max Activating Token Index: 604

Text #12

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7473. Min Act: -0.0002

Data Index: 1458256 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8157. Min Act: -0.0002

Data Index: 1508611 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7888. Min Act: -0.0002

Data Index: 1385842 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7653. Min Act: -0.0002

Data Index: 1581912 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7910. Min Act: -0.0002

Data Index: 1426376 (Python Code)

Max Activating Token Index: 731

Text #17

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7888. Min Act: -0.0002

Data Index: 1503940 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7592. Min Act: -0.0002

Data Index: 1405873 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7551. Min Act: -0.0002

Data Index: 1633120 (Python Code)

Max Activating Token Index: 916