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

Dataset: The Pile

Neuron 298 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4176. Min Act: -0.0000

Data Index: 440517 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.5689. Min Act: -0.0000

Data Index: 143758 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1694744 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1926289 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2790. Min Act: -0.0000

Data Index: 780416 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2798. Min Act: -0.0000

Data Index: 479968 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1716370 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3187. Min Act: -0.0000

Data Index: 190449 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2813. Min Act: -0.0000

Data Index: 395432 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1282490 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1592. Min Act: -0.0000

Data Index: 34491 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2039. Min Act: 0.0000

Data Index: 1444429 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.0651. Min Act: -0.0000

Data Index: 168594 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1214. Min Act: -0.0000

Data Index: 289718 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.0999. Min Act: -0.0000

Data Index: 512723 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1923. Min Act: -0.0000

Data Index: 147439 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1460632 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.0899. Min Act: -0.0000

Data Index: 927474 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1791945 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.0528. Min Act: 0.0000

Data Index: 1598908 (The Pile)

Max Activating Token Index: 471