Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1518 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0002

Data Index: 1495419 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5343. Min Act: -0.0002

Data Index: 1525794 (Python Code)

Max Activating Token Index: 969

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5360. Min Act: -0.0002

Data Index: 1560904 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5229. Min Act: -0.0002

Data Index: 605891 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4813. Min Act: -0.0002

Data Index: 1617829 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4794. Min Act: -0.0002

Data Index: 1459154 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4587. Min Act: -0.0002

Data Index: 1420200 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5173. Min Act: -0.0002

Data Index: 1441319 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4888. Min Act: -0.0002

Data Index: 1605838 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4838. Min Act: -0.0002

Data Index: 1566124 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4816. Min Act: -0.0002

Data Index: 1412147 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4780. Min Act: -0.0002

Data Index: 1577762 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4584. Min Act: -0.0002

Data Index: 1513130 (Python Code)

Max Activating Token Index: 965

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4886. Min Act: -0.0002

Data Index: 1567393 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4439. Min Act: -0.0002

Data Index: 1524089 (Python Code)

Max Activating Token Index: 623

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4694. Min Act: -0.0002

Data Index: 1639567 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4841. Min Act: -0.0002

Data Index: 1626929 (Python Code)

Max Activating Token Index: 869

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4810. Min Act: -0.0002

Data Index: 1255846 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4494. Min Act: -0.0002

Data Index: 1436347 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4598. Min Act: -0.0002

Data Index: 1640095 (Python Code)

Max Activating Token Index: 618