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

Dataset: The Pile

Neuron 1881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1291666 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 1.0095. Min Range: -1.0095

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1606537 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1990493 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1294439 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1591097 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8104. Min Act: 0.0000

Data Index: 146413 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1388889 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8322. Min Act: 0.0000

Data Index: 1786704 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8250. Min Act: 0.0000

Data Index: 125191 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.6953. Min Act: -0.0000

Data Index: 572900 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8207. Min Act: -0.0000

Data Index: 595160 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8227. Min Act: -0.0000

Data Index: 907947 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7717. Min Act: 0.0000

Data Index: 1757990 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7343. Min Act: 0.0000

Data Index: 726965 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8281. Min Act: 0.0000

Data Index: 1406417 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1151572 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7777. Min Act: -0.0000

Data Index: 288770 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7675. Min Act: -0.0000

Data Index: 807098 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7879. Min Act: -0.0000

Data Index: 283891 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1472462 (The Pile)

Max Activating Token Index: 88