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

Dataset: The Pile

Neuron 1575 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7437. Min Act: 0.0000

Data Index: 1146362 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1980198 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7742. Min Act: -0.0000

Data Index: 121936 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7244. Min Act: -0.0000

Data Index: 667920 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1993916 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1174629 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1542641 (The Pile)

Max Activating Token Index: 804

Text #7

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1244575 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1929016 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6312. Min Act: -0.0000

Data Index: 840005 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6081. Min Act: -0.0000

Data Index: 8551 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6614. Min Act: -0.0000

Data Index: 427853 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1957621 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1232246 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1254078 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5598. Min Act: -0.0000

Data Index: 876368 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5625. Min Act: -0.0000

Data Index: 297767 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5278. Min Act: -0.0000

Data Index: 173072 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1006524 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5505. Min Act: -0.0000

Data Index: 884429 (The Pile)

Max Activating Token Index: 390