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

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

Neuron 1559 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0200. Min Range: -1.0200

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1499675 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1597175 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1618888 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1438388 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1440688 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1509176 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1612471 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1622677 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1521326 (Python Code)

Max Activating Token Index: 144

Text #9

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1592824 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1389783 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1545277 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1418512 (Python Code)

Max Activating Token Index: 657

Text #13

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1596965 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1476183 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1401873 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1521022 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1404487 (Python Code)

Max Activating Token Index: 193

Text #18

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1588771 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1412871 (Python Code)

Max Activating Token Index: 237