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

Dataset: The Pile

Neuron 2845 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: 0.8560. Min Range: -0.8560

Max Act: 0.8192. Min Act: -0.0000

Data Index: 487309 (The Pile)

Max Activating Token Index: 896

Text #1

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1113687 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.8560. Min Act: 0.0000

Data Index: 1415796 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.7055. Min Act: -0.0000

Data Index: 341297 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1014409 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1684102 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1076509 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6688. Min Act: -0.0000

Data Index: 892479 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6478. Min Act: -0.0000

Data Index: 78319 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1594929 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1716356 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1781772 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1064997 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1134663 (The Pile)

Max Activating Token Index: 565

Text #14

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6090. Min Act: -0.0000

Data Index: 733163 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1810030 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1138207 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1470702 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.5987. Min Act: -0.0000

Data Index: 733324 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 0.8560. Min Range: -0.8560

Max Act: 0.5734. Min Act: -0.0000

Data Index: 366657 (The Pile)

Max Activating Token Index: 861