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

Dataset: The Pile

Neuron 1547 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: 0.1306. Min Range: -0.1306

Max Act: 0.1306. Min Act: -0.0000

Data Index: 761307 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1234. Min Act: -0.0000

Data Index: 971812 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1832081 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1909607 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1083. Min Act: -0.0000

Data Index: 977589 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1608952 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1119967 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0940. Min Act: -0.0000

Data Index: 447952 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0918. Min Act: -0.0000

Data Index: 473687 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1886750 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1046414 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1931366 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1689349 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0755. Min Act: -0.0000

Data Index: 62714 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0820. Min Act: -0.0000

Data Index: 68696 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1639450 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1124261 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1848563 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1517763 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1656278 (The Pile)

Max Activating Token Index: 856