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

Dataset: The Pile

Neuron 2736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.4068. Min Act: -0.0000

Data Index: 669550 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2926. Min Act: -0.0000

Data Index: 59679 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1913828 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1475632 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1301166 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2271. Min Act: -0.0000

Data Index: 822775 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2096. Min Act: -0.0000

Data Index: 361254 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1181814 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1431962 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1852. Min Act: -0.0000

Data Index: 243198 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1871556 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1700. Min Act: -0.0000

Data Index: 403293 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1710. Min Act: -0.0000

Data Index: 39498 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1598. Min Act: -0.0000

Data Index: 321505 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1692. Min Act: -0.0000

Data Index: 255317 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1364142 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1019033 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1727. Min Act: -0.0000

Data Index: 592451 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1828. Min Act: -0.0000

Data Index: 456068 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1502446 (The Pile)

Max Activating Token Index: 828