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

Dataset: The Pile

Neuron 2135 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.8752. Min Act: -0.0000

Data Index: 1943523 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.4408. Min Act: -0.0000

Data Index: 959835 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.6034. Min Act: -0.0000

Data Index: 323494 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.4927. Min Act: -0.0000

Data Index: 884102 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.5517. Min Act: -0.0000

Data Index: 478418 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.2165. Min Act: -0.0000

Data Index: 106477 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1847153 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1305964 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.4194. Min Act: -0.0000

Data Index: 313898 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.2214. Min Act: -0.0000

Data Index: 441219 (The Pile)

Max Activating Token Index: 533

Text #10

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.3128. Min Act: -0.0000

Data Index: 1359421 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.3020. Min Act: -0.0000

Data Index: 737656 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1854997 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1775463 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1251307 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1348673 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1815235 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.2240. Min Act: -0.0000

Data Index: 858504 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.1886. Min Act: -0.0000

Data Index: 521824 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1436097 (The Pile)

Max Activating Token Index: 327