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

Dataset: The Pile

Neuron 3567 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: 0.9150. Min Range: -0.9150

Max Act: 0.9150. Min Act: -0.0000

Data Index: 136283 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1735046 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1724308 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1788000 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5647. Min Act: -0.0000

Data Index: 441208 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6346. Min Act: -0.0000

Data Index: 479289 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6014. Min Act: -0.0000

Data Index: 757411 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1645409 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1803848 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1760342 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1095138 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1979261 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1406963 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5033. Min Act: -0.0000

Data Index: 316807 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5434. Min Act: -0.0000

Data Index: 47991 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1825715 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6418. Min Act: -0.0000

Data Index: 189197 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5272. Min Act: -0.0000

Data Index: 139790 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1942174 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1389539 (The Pile)

Max Activating Token Index: 772