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

Dataset: The Pile

Neuron 4531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1927239 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.7415. Min Act: -0.0000

Data Index: 193077 (The Pile)

Max Activating Token Index: 811

Text #2

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1116145 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6914. Min Act: -0.0000

Data Index: 189425 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1941454 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1675081 (The Pile)

Max Activating Token Index: 914

Text #6

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6383. Min Act: -0.0000

Data Index: 821050 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6596. Min Act: -0.0000

Data Index: 299928 (The Pile)

Max Activating Token Index: 209

Text #8

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6346. Min Act: -0.0000

Data Index: 151862 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6409. Min Act: -0.0000

Data Index: 47607 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6503. Min Act: -0.0000

Data Index: 635861 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1019985 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1621734 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5868. Min Act: -0.0000

Data Index: 875332 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1052536 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5989. Min Act: -0.0000

Data Index: 680993 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1511000 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1045012 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1501472 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5721. Min Act: -0.0000

Data Index: 488018 (The Pile)

Max Activating Token Index: 223