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

Dataset: The Pile

Neuron 3270 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: 1.0779. Min Range: -1.0779

Max Act: 1.0614. Min Act: -0.0000

Data Index: 441873 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0102. Min Act: 0.0000

Data Index: 1855217 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0779. Min Act: 0.0000

Data Index: 253490 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9352. Min Act: 0.0000

Data Index: 1222868 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0187. Min Act: -0.0000

Data Index: 760744 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9458. Min Act: 0.0000

Data Index: 1003055 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9407. Min Act: 0.0000

Data Index: 1506997 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9446. Min Act: 0.0000

Data Index: 985901 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1417962 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9021. Min Act: 0.0000

Data Index: 1939274 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1281263 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8532. Min Act: 0.0000

Data Index: 878912 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8988. Min Act: 0.0000

Data Index: 1143672 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1761068 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7877. Min Act: 0.0001

Data Index: 887188 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9337. Min Act: 0.0001

Data Index: 1091764 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8014. Min Act: 0.0000

Data Index: 933414 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8408. Min Act: 0.0000

Data Index: 1706663 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1769544 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1080648 (The Pile)

Max Activating Token Index: 437