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

Dataset: The Pile

Neuron 1756 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: 0.7820. Min Range: -0.7820

Max Act: 0.7779. Min Act: -0.0000

Data Index: 614739 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7367. Min Act: -0.0000

Data Index: 283720 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7820. Min Act: -0.0000

Data Index: 899624 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7105. Min Act: -0.0000

Data Index: 797003 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1296985 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1663298 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6734. Min Act: -0.0000

Data Index: 986491 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6446. Min Act: -0.0000

Data Index: 333180 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1037284 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6476. Min Act: -0.0000

Data Index: 421437 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6284. Min Act: -0.0000

Data Index: 118471 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6393. Min Act: -0.0000

Data Index: 363372 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1265769 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6337. Min Act: -0.0000

Data Index: 84522 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1048681 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6212. Min Act: -0.0000

Data Index: 16239 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6030. Min Act: -0.0000

Data Index: 361014 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6057. Min Act: -0.0000

Data Index: 312037 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6235. Min Act: -0.0000

Data Index: 525776 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5995. Min Act: -0.0000

Data Index: 269844 (The Pile)

Max Activating Token Index: 610