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

Dataset: The Pile

Neuron 2751 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1647698 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1205034 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.1402. Min Act: -0.0000

Data Index: 782758 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.0835. Min Act: -0.0000

Data Index: 822079 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.0549. Min Act: -0.0000

Data Index: 889851 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1692699 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.0184. Min Act: -0.0000

Data Index: 525107 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1994944 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 1.1877. Min Range: -1.1877

Max Act: 1.0356. Min Act: -0.0000

Data Index: 604755 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9694. Min Act: -0.0000

Data Index: 845513 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9791. Min Act: -0.0000

Data Index: 972389 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9995. Min Act: -0.0000

Data Index: 756287 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9552. Min Act: -0.0000

Data Index: 600322 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9576. Min Act: -0.0000

Data Index: 285144 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9440. Min Act: -0.0000

Data Index: 326441 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1038142 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9753. Min Act: -0.0000

Data Index: 991645 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1156343 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 1.1877. Min Range: -1.1877

Max Act: 0.9500. Min Act: -0.0000

Data Index: 398446 (The Pile)

Max Activating Token Index: 751