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

Dataset: The Pile

Neuron 3902 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: 0.8411. Min Range: -0.8411

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1129837 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1408447 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8373. Min Act: -0.0000

Data Index: 312944 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7590. Min Act: -0.0000

Data Index: 537250 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1832405 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1934833 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7647. Min Act: -0.0000

Data Index: 217275 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7365. Min Act: -0.0000

Data Index: 670927 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7560. Min Act: -0.0000

Data Index: 633327 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7512. Min Act: -0.0000

Data Index: 199828 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1563804 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1101769 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6923. Min Act: -0.0000

Data Index: 50837 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1448867 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1278200 (The Pile)

Max Activating Token Index: 196

Text #15

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1205170 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1795425 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7323. Min Act: -0.0000

Data Index: 685915 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5957. Min Act: -0.0000

Data Index: 132154 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6395. Min Act: -0.0000

Data Index: 191826 (The Pile)

Max Activating Token Index: 996