Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4601 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.9592. Min Act: -0.0000

Data Index: 1426424 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.9216. Min Act: -0.0000

Data Index: 1630202 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1563943 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.8836. Min Act: -0.0000

Data Index: 580516 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.6727. Min Act: -0.0000

Data Index: 732218 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.6212. Min Act: -0.0000

Data Index: 843708 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.5314. Min Act: -0.0000

Data Index: 568753 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.6092. Min Act: -0.0000

Data Index: 1639703 (Python Code)

Max Activating Token Index: 362

Text #8

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.4834. Min Act: -0.0000

Data Index: 826962 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.5281. Min Act: -0.0000

Data Index: 1650097 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.5420. Min Act: -0.0000

Data Index: 89499 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.4212. Min Act: -0.0000

Data Index: 212572 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.5132. Min Act: -0.0000

Data Index: 289019 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1548728 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1636575 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.4438. Min Act: -0.0000

Data Index: 761061 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1336855 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1366020 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1615958 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 1.9592. Min Range: -1.9592

Max Act: 1.3673. Min Act: -0.0000

Data Index: 1476503 (Python Code)

Max Activating Token Index: 703