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

Dataset: The Pile

Neuron 2907 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: 0.5556. Min Range: -0.5556

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1434991 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1106948 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1608710 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4872. Min Act: -0.0000

Data Index: 47852 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1596679 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4992. Min Act: -0.0000

Data Index: 619539 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1574054 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1526466 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4437. Min Act: -0.0000

Data Index: 390505 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4404. Min Act: -0.0000

Data Index: 182826 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4329. Min Act: -0.0000

Data Index: 674991 (The Pile)

Max Activating Token Index: 61

Text #11

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4413. Min Act: -0.0000

Data Index: 894339 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4149. Min Act: -0.0000

Data Index: 914646 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4266. Min Act: -0.0000

Data Index: 535205 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4091. Min Act: -0.0000

Data Index: 709089 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4127. Min Act: -0.0000

Data Index: 63320 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1504177 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1996207 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4187. Min Act: -0.0000

Data Index: 428940 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4163. Min Act: -0.0000

Data Index: 179841 (The Pile)

Max Activating Token Index: 668