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

Dataset: The Pile

Neuron 4676 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: 1.8793. Min Range: -1.8793

Max Act: 1.8793. Min Act: -0.0000

Data Index: 847568 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.6419. Min Act: -0.0000

Data Index: 488272 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.5881. Min Act: -0.0000

Data Index: 712973 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3999. Min Act: -0.0000

Data Index: 332486 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.4165. Min Act: -0.0000

Data Index: 1294407 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1023026 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3086. Min Act: -0.0000

Data Index: 288300 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1681292 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1118870 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2806. Min Act: -0.0000

Data Index: 843839 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3466. Min Act: -0.0000

Data Index: 500185 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1958749 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2398. Min Act: -0.0000

Data Index: 750784 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.1460. Min Act: -0.0000

Data Index: 277194 (The Pile)

Max Activating Token Index: 50

Text #14

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1292691 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2079. Min Act: -0.0000

Data Index: 760517 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1709963 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3472. Min Act: -0.0000

Data Index: 962157 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2534. Min Act: -0.0000

Data Index: 449323 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1745592 (The Pile)

Max Activating Token Index: 614