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

Dataset: The Pile

Neuron 506 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: 0.7552. Min Range: -0.7552

Max Act: 0.7552. Min Act: -0.0000

Data Index: 60132 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1436454 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1443255 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1861232 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1942805 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6643. Min Act: 0.0000

Data Index: 1360535 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6275. Min Act: -0.0000

Data Index: 38570 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6096. Min Act: -0.0000

Data Index: 145592 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1225116 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1142 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5269. Min Act: -0.0000

Data Index: 757959 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5730. Min Act: -0.0000

Data Index: 661239 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5212. Min Act: -0.0000

Data Index: 989794 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5454. Min Act: -0.0000

Data Index: 663195 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1763624 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1045891 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4931. Min Act: -0.0000

Data Index: 616344 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4333. Min Act: -0.0000

Data Index: 452799 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5017. Min Act: 0.0000

Data Index: 1313356 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4731. Min Act: -0.0000

Data Index: 705330 (The Pile)

Max Activating Token Index: 899