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

Dataset: The Pile

Neuron 3075 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: 0.7774. Min Range: -0.7774

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1919945 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1569541 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6739. Min Act: -0.0000

Data Index: 287768 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1390840 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6164. Min Act: -0.0000

Data Index: 223412 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1255472 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1062362 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1879454 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1725834 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1601569 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5013. Min Act: -0.0000

Data Index: 143060 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1499813 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1786252 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.4960. Min Act: -0.0000

Data Index: 993228 (The Pile)

Max Activating Token Index: 75

Text #14

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5260. Min Act: -0.0000

Data Index: 679481 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1072268 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5057. Min Act: -0.0000

Data Index: 231338 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.4741. Min Act: -0.0000

Data Index: 451560 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1016803 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.4591. Min Act: -0.0000

Data Index: 760661 (The Pile)

Max Activating Token Index: 371