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

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

Neuron 1882 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: 0.0977. Min Range: -0.0977

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1377824 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1607147 (Python Code)

Max Activating Token Index: 234

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1568421 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1480952 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1545082 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1500301 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1537092 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1579005 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1613291 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1645157 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1407843 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1655690 (Python Code)

Max Activating Token Index: 915

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1622775 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1486132 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1615585 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1458401 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1510067 (Python Code)

Max Activating Token Index: 64

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1561325 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1422362 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1568196 (Python Code)

Max Activating Token Index: 10