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

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

Neuron 2402 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: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1495467 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1625952 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1623361 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1572238 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1579217 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1563256 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1402370 (Python Code)

Max Activating Token Index: 669

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1443091 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1599369 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1593830 (Python Code)

Max Activating Token Index: 329

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1370380 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1636485 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1574636 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1453996 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1407702 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1590531 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1430299 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1401598 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1424281 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1509850 (Python Code)

Max Activating Token Index: 949