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

Dataset: The Pile

Neuron 3491 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: 1.0394. Min Range: -1.0394

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1149712 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.9235. Min Act: 0.0000

Data Index: 1714524 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8966. Min Act: 0.0000

Data Index: 555468 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8133. Min Act: -0.0000

Data Index: 65751 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1827964 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1618622 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8195. Min Act: 0.0000

Data Index: 450008 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1883349 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8048. Min Act: 0.0000

Data Index: 1069996 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1619654 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8013. Min Act: -0.0000

Data Index: 794594 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7579. Min Act: 0.0000

Data Index: 1020290 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1118858 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8115. Min Act: 0.0000

Data Index: 1103606 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7656. Min Act: -0.0000

Data Index: 430374 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1935958 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8014. Min Act: 0.0000

Data Index: 1964310 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1277875 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7674. Min Act: 0.0000

Data Index: 1430282 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1810834 (The Pile)

Max Activating Token Index: 465