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

Dataset: The Pile

Neuron 2053 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.9268. Min Act: -0.0001

Data Index: 1852974 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1701463 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1371761 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1812088 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1677631 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1418799 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1660219 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1684081 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7959. Min Act: -0.0000

Data Index: 497879 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7371. Min Act: -0.0000

Data Index: 796471 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1891394 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1557562 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7336. Min Act: -0.0000

Data Index: 607604 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1250828 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7016. Min Act: -0.0000

Data Index: 719804 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1503218 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1622848 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7479. Min Act: -0.0000

Data Index: 564786 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1846454 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6807. Min Act: -0.0000

Data Index: 155800 (The Pile)

Max Activating Token Index: 535