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

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

Neuron 4056 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: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0002

Data Index: 325253 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1048002 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0875. Min Act: -0.0002

Data Index: 909515 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0847. Min Act: -0.0002

Data Index: 512316 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0843. Min Act: -0.0002

Data Index: 106816 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0805. Min Act: -0.0002

Data Index: 599225 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0782. Min Act: -0.0002

Data Index: 838714 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0772. Min Act: -0.0002

Data Index: 776255 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0778. Min Act: -0.0002

Data Index: 308513 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0747. Min Act: -0.0002

Data Index: 67277 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0729. Min Act: -0.0002

Data Index: 10284 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1321104 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0694. Min Act: -0.0002

Data Index: 880045 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0709. Min Act: -0.0002

Data Index: 172245 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0703. Min Act: -0.0002

Data Index: 391165 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1171593 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0659. Min Act: -0.0002

Data Index: 46142 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0653. Min Act: -0.0002

Data Index: 318708 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0644. Min Act: -0.0002

Data Index: 595462 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1359690 (C4 (Web Text))

Max Activating Token Index: 601