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

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

Neuron 2477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7864. Min Act: -0.0002

Data Index: 1364148 (Python Code)

Max Activating Token Index: 497

Text #1

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7408. Min Act: -0.0002

Data Index: 1577435 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6713. Min Act: -0.0002

Data Index: 1608284 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6702. Min Act: -0.0002

Data Index: 1527643 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6635. Min Act: -0.0002

Data Index: 1623751 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6490. Min Act: -0.0002

Data Index: 1367190 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6373. Min Act: -0.0002

Data Index: 1453515 (Python Code)

Max Activating Token Index: 808

Text #7

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6117. Min Act: -0.0002

Data Index: 1590648 (Python Code)

Max Activating Token Index: 245

Text #8

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6389. Min Act: -0.0002

Data Index: 1627696 (Python Code)

Max Activating Token Index: 377

Text #9

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6678. Min Act: -0.0002

Data Index: 1467454 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6416. Min Act: -0.0002

Data Index: 958765 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5906. Min Act: -0.0002

Data Index: 1609600 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5973. Min Act: -0.0002

Data Index: 1210979 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6228. Min Act: -0.0002

Data Index: 1580699 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5708. Min Act: -0.0002

Data Index: 1466603 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6051. Min Act: -0.0002

Data Index: 1542961 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5776. Min Act: -0.0002

Data Index: 1395822 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6188. Min Act: -0.0002

Data Index: 1386897 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6265. Min Act: -0.0002

Data Index: 1387978 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5333. Min Act: -0.0002

Data Index: 1434871 (Python Code)

Max Activating Token Index: 861