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

Dataset: The Pile

Neuron 1833 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.6245. Min Act: -0.0000

Data Index: 808650 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.6707. Min Act: -0.0000

Data Index: 154220 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4830. Min Act: -0.0000

Data Index: 33720 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5730. Min Act: -0.0000

Data Index: 356242 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4806. Min Act: -0.0000

Data Index: 1897165 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3298. Min Act: -0.0000

Data Index: 956744 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4571. Min Act: -0.0000

Data Index: 852484 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2081. Min Act: -0.0000

Data Index: 639179 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.0195. Min Act: -0.0000

Data Index: 568385 (The Pile)

Max Activating Token Index: 688

Text #9

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.0249. Min Act: -0.0000

Data Index: 1496043 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4540. Min Act: -0.0000

Data Index: 1048558 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3176. Min Act: -0.0000

Data Index: 135054 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.1260. Min Act: -0.0000

Data Index: 577242 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.0974. Min Act: -0.0000

Data Index: 652690 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.0383. Min Act: -0.0000

Data Index: 157689 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 3.6707. Min Range: -3.6707

Max Act: 2.8690. Min Act: -0.0000

Data Index: 613395 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.0966. Min Act: -0.0000

Data Index: 589649 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2838. Min Act: -0.0000

Data Index: 375270 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.0996. Min Act: -0.0000

Data Index: 1247779 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 3.6707. Min Range: -3.6707

Max Act: 2.9283. Min Act: -0.0000

Data Index: 1296745 (The Pile)

Max Activating Token Index: 339