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

Dataset: The Pile

Neuron 3584 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5145. Min Act: -0.0000

Data Index: 395378 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1142991 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5211. Min Act: -0.0000

Data Index: 623783 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4875. Min Act: -0.0000

Data Index: 649345 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4356. Min Act: -0.0000

Data Index: 781950 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4378. Min Act: -0.0000

Data Index: 598197 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1178277 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1059549 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4353. Min Act: -0.0000

Data Index: 963035 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4421. Min Act: -0.0000

Data Index: 303936 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3938. Min Act: -0.0000

Data Index: 873500 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1162633 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4191. Min Act: -0.0000

Data Index: 531163 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1343597 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4213. Min Act: -0.0000

Data Index: 948100 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1095672 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1413176 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3800. Min Act: -0.0000

Data Index: 974300 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1447765 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1846206 (The Pile)

Max Activating Token Index: 229