Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1586810 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4923. Min Act: -0.0000

Data Index: 223578 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4571. Min Act: -0.0000

Data Index: 426880 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1226091 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1596187 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1075318 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4697. Min Act: -0.0000

Data Index: 532257 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3842. Min Act: -0.0000

Data Index: 825276 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4562. Min Act: 0.0000

Data Index: 936847 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1586890 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4598. Min Act: -0.0000

Data Index: 203424 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1632684 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4712. Min Act: -0.0000

Data Index: 110132 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1770996 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4692. Min Act: -0.0000

Data Index: 691591 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1000149 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4551. Min Act: -0.0000

Data Index: 593738 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4224. Min Act: -0.0000

Data Index: 712888 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1754245 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1049817 (The Pile)

Max Activating Token Index: 404