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

Dataset: The Pile

Neuron 2857 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: 0.9905. Min Range: -0.9905

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1365772 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9905. Min Act: -0.0000

Data Index: 873054 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1054617 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9664. Min Act: -0.0000

Data Index: 456915 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8143. Min Act: -0.0000

Data Index: 981067 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1160680 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9005. Min Act: -0.0000

Data Index: 38414 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1269855 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1397368 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1798807 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8621. Min Act: -0.0000

Data Index: 686277 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9155. Min Act: -0.0000

Data Index: 236422 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1622676 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1585729 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1169373 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1096411 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8898. Min Act: -0.0000

Data Index: 867803 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8528. Min Act: -0.0000

Data Index: 643445 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1903423 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1255174 (The Pile)

Max Activating Token Index: 290