Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 24 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.2788. Min Act: -0.0000

Data Index: 466390 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1833. Min Act: -0.0000

Data Index: 251908 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1358. Min Act: -0.0000

Data Index: 351382 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0104. Min Act: -0.0000

Data Index: 592259 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1268. Min Act: -0.0000

Data Index: 645099 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1059774 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9879. Min Act: -0.0000

Data Index: 634117 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1122764 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0005. Min Act: -0.0000

Data Index: 364469 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9845. Min Act: -0.0000

Data Index: 194744 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1728826 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1486520 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1836669 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1812816 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1861481 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1318250 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9554. Min Act: -0.0000

Data Index: 816494 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1595896 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1884962 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9798. Min Act: -0.0000

Data Index: 376421 (The Pile)

Max Activating Token Index: 735