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

Dataset: The Pile

Neuron 474 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: 0.8230. Min Range: -0.8230

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1963392 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.6626. Min Act: -0.0000

Data Index: 590219 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1199729 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5511. Min Act: -0.0000

Data Index: 6506 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5250. Min Act: -0.0000

Data Index: 448806 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1042407 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1526136 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5435. Min Act: -0.0000

Data Index: 161842 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5231. Min Act: -0.0000

Data Index: 701131 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1618674 (The Pile)

Max Activating Token Index: 572

Text #10

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1542249 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4304. Min Act: -0.0000

Data Index: 942599 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1609481 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1975406 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4529. Min Act: -0.0000

Data Index: 331525 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1331153 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4054. Min Act: -0.0000

Data Index: 311499 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1402261 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.3644. Min Act: -0.0000

Data Index: 806592 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1658630 (The Pile)

Max Activating Token Index: 671