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

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

Neuron 3461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0994. Min Act: -0.0002

Data Index: 143160 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0913. Min Act: -0.0002

Data Index: 867714 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1568978 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1273403 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0798. Min Act: -0.0002

Data Index: 30104 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0801. Min Act: -0.0002

Data Index: 159015 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0773. Min Act: -0.0002

Data Index: 14083 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0798. Min Act: -0.0002

Data Index: 254629 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0793. Min Act: -0.0002

Data Index: 546853 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1038237 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1134325 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1055013 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0756. Min Act: -0.0002

Data Index: 341526 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0778. Min Act: -0.0002

Data Index: 905832 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0772. Min Act: -0.0002

Data Index: 834835 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1308644 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0774. Min Act: -0.0002

Data Index: 617518 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0767. Min Act: -0.0002

Data Index: 283107 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0750. Min Act: -0.0002

Data Index: 288418 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0751. Min Act: -0.0002

Data Index: 933765 (C4 (Web Text))

Max Activating Token Index: 445