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

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

Neuron 118 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: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0002

Data Index: 1447261 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1455692 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1642051 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1427776 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1623724 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1473730 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1539374 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1619391 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1452863 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1438306 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1542918 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1637696 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1454737 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1386371 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1452849 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1480373 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1451354 (Python Code)

Max Activating Token Index: 442

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1455780 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1620867 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1265351 (C4 (Web Text))

Max Activating Token Index: 127