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

Dataset: The Pile

Neuron 715 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: 1.7116. Min Range: -1.7116

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1634688 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6354. Min Act: -0.0000

Data Index: 1257598 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1135861 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.7116. Min Act: -0.0000

Data Index: 133893 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6703. Min Act: -0.0000

Data Index: 788874 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6734. Min Act: -0.0000

Data Index: 589273 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6737. Min Act: -0.0000

Data Index: 1468341 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5470. Min Act: -0.0000

Data Index: 1987286 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6199. Min Act: -0.0000

Data Index: 875732 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.7110. Min Act: -0.0000

Data Index: 1581422 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5725. Min Act: -0.0000

Data Index: 1016173 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1452886 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5126. Min Act: -0.0000

Data Index: 487039 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1198884 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1597415 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4734. Min Act: -0.0000

Data Index: 725358 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3959. Min Act: -0.0000

Data Index: 1438476 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4590. Min Act: -0.0000

Data Index: 1581110 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1940993 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1357779 (The Pile)

Max Activating Token Index: 296