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

Dataset: The Pile

Neuron 4881 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.8260. Min Act: -0.0000

Data Index: 88482 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1595223 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1929174 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1005516 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1717668 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5960. Min Act: -0.0000

Data Index: 856138 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6537. Min Act: -0.0000

Data Index: 771746 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5409. Min Act: -0.0000

Data Index: 689664 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1512441 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1480207 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1820857 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1048010 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1481627 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1654278 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1085513 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1677206 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5145. Min Act: -0.0000

Data Index: 602522 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4078. Min Act: -0.0000

Data Index: 493863 (The Pile)

Max Activating Token Index: 770

Text #18

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1004200 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4752. Min Act: -0.0000

Data Index: 24082 (The Pile)

Max Activating Token Index: 41