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

Dataset: The Pile

Neuron 1358 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: 0.8071. Min Range: -0.8071

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1521324 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6863. Min Act: -0.0000

Data Index: 360514 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1570838 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1828781 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.7313. Min Act: -0.0000

Data Index: 465445 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6587. Min Act: -0.0000

Data Index: 846374 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1140472 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1817055 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1078995 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1661270 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1557133 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1930873 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6084. Min Act: -0.0000

Data Index: 326568 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6292. Min Act: -0.0000

Data Index: 103763 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1664848 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1555345 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1691483 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6096. Min Act: -0.0000

Data Index: 713026 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1841300 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6053. Min Act: -0.0000

Data Index: 602851 (The Pile)

Max Activating Token Index: 527