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

Dataset: The Pile

Neuron 283 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: 1.5833. Min Range: -1.5833

Max Act: 1.4598. Min Act: -0.0000

Data Index: 74748 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.5411. Min Act: -0.0000

Data Index: 565829 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.5104. Min Act: -0.0000

Data Index: 951303 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.5833. Min Act: -0.0000

Data Index: 822371 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.4727. Min Act: -0.0000

Data Index: 1484415 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1362758 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.5087. Min Act: -0.0000

Data Index: 1199700 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3526. Min Act: -0.0000

Data Index: 613485 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1418354 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2934. Min Act: -0.0000

Data Index: 954611 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1854475 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2834. Min Act: -0.0000

Data Index: 218234 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1133898 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1508338 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2710. Min Act: -0.0000

Data Index: 517162 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1513658 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3273. Min Act: -0.0000

Data Index: 516574 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2542. Min Act: -0.0000

Data Index: 207478 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2573. Min Act: -0.0000

Data Index: 744226 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3285. Min Act: -0.0000

Data Index: 805599 (The Pile)

Max Activating Token Index: 832