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

Dataset: The Pile

Neuron 3313 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9641. Min Act: -0.0000

Data Index: 537858 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1691094 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1404473 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1442119 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7970. Min Act: -0.0000

Data Index: 531854 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1035137 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8392. Min Act: -0.0000

Data Index: 362221 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7920. Min Act: -0.0000

Data Index: 435805 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1194351 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1418040 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1512161 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8367. Min Act: -0.0000

Data Index: 448637 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7128. Min Act: -0.0000

Data Index: 575860 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7616. Min Act: -0.0000

Data Index: 638590 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7583. Min Act: -0.0000

Data Index: 324395 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7632. Min Act: -0.0000

Data Index: 656456 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9590. Min Act: -0.0000

Data Index: 765244 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7373. Min Act: -0.0000

Data Index: 761990 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7113. Min Act: -0.0000

Data Index: 425237 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1548284 (The Pile)

Max Activating Token Index: 832