Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2014. Min Act: -0.0001

Data Index: 566205 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2200. Min Act: -0.0001

Data Index: 620656 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1914. Min Act: -0.0001

Data Index: 796426 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1950. Min Act: -0.0001

Data Index: 64181 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1359346 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1062573 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1773. Min Act: -0.0001

Data Index: 71308 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1138515 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1674. Min Act: -0.0001

Data Index: 796855 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1730. Min Act: -0.0001

Data Index: 756809 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1672. Min Act: -0.0001

Data Index: 411150 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1620. Min Act: -0.0001

Data Index: 819996 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1597. Min Act: -0.0001

Data Index: 876374 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1631. Min Act: -0.0000

Data Index: 238966 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1647. Min Act: -0.0001

Data Index: 719247 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1164266 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1333382 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1605. Min Act: -0.0001

Data Index: 110884 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1666. Min Act: -0.0001

Data Index: 55296 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1602. Min Act: -0.0001

Data Index: 654616 (C4 (Web Text))

Max Activating Token Index: 568