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

Dataset: The Pile

Neuron 2201 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: 3.0912. Min Range: -3.0912

Max Act: 2.9266. Min Act: -0.0000

Data Index: 761860 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0103. Min Act: -0.0000

Data Index: 238453 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9839. Min Act: -0.0000

Data Index: 1373037 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8180. Min Act: -0.0000

Data Index: 159482 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0912. Min Act: -0.0000

Data Index: 911111 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8683. Min Act: -0.0000

Data Index: 539906 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.6315. Min Act: -0.0000

Data Index: 366057 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.6179. Min Act: -0.0000

Data Index: 1092052 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.5752. Min Act: -0.0000

Data Index: 143747 (The Pile)

Max Activating Token Index: 755

Text #9

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.7765. Min Act: -0.0000

Data Index: 1490443 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.6147. Min Act: -0.0000

Data Index: 351920 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.5965. Min Act: -0.0000

Data Index: 1219440 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.5730. Min Act: -0.0000

Data Index: 542543 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.5817. Min Act: -0.0000

Data Index: 1363048 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1595864 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.4852. Min Act: -0.0000

Data Index: 961657 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.4825. Min Act: -0.0000

Data Index: 1149584 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.4843. Min Act: -0.0000

Data Index: 285740 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1747949 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.4593. Min Act: -0.0000

Data Index: 1796763 (The Pile)

Max Activating Token Index: 252