Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3851 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1595871 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1936482 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1820312 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1841905 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8469. Min Act: -0.0000

Data Index: 594956 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8091. Min Act: -0.0000

Data Index: 139790 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1749668 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7848. Min Act: -0.0000

Data Index: 702855 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1244314 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1079543 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7846. Min Act: -0.0000

Data Index: 748748 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1773822 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6545. Min Act: -0.0000

Data Index: 852860 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6287. Min Act: 0.0000

Data Index: 823853 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7214. Min Act: -0.0000

Data Index: 733380 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7011. Min Act: -0.0000

Data Index: 293852 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6581. Min Act: -0.0000

Data Index: 165810 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6208. Min Act: -0.0000

Data Index: 200222 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6267. Min Act: -0.0000

Data Index: 17182 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6330. Min Act: -0.0000

Data Index: 505916 (The Pile)

Max Activating Token Index: 974