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

Dataset: The Pile

Neuron 2713 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: 1.5386. Min Range: -1.5386

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1957429 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1524025 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1925272 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1105233 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1718760 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1683538 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1700663 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1563733 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0281. Min Act: -0.0000

Data Index: 741514 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0090. Min Act: -0.0000

Data Index: 58447 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0208. Min Act: -0.0000

Data Index: 734920 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1350767 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1031389 (The Pile)

Max Activating Token Index: 995

Text #13

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1301708 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9607. Min Act: -0.0000

Data Index: 1364346 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1745592 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1075284 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9605. Min Act: -0.0000

Data Index: 201113 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1404790 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.5386. Min Range: -1.5386

Max Act: 0.9441. Min Act: -0.0000

Data Index: 878967 (The Pile)

Max Activating Token Index: 749