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

Dataset: The Pile

Neuron 3992 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: 1.1516. Min Range: -1.1516

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1714287 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9106. Min Act: -0.0000

Data Index: 929362 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1235144 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1591448 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7719. Min Act: -0.0000

Data Index: 138366 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7623. Min Act: -0.0000

Data Index: 872416 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1595922 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1087033 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7206. Min Act: -0.0000

Data Index: 767441 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1458713 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1633261 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1098815 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1475127 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1080152 (The Pile)

Max Activating Token Index: 587

Text #14

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6517. Min Act: 0.0001

Data Index: 238305 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1292037 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6105. Min Act: -0.0000

Data Index: 54216 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6051. Min Act: -0.0000

Data Index: 783481 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1720893 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.6086. Min Act: -0.0000

Data Index: 271197 (The Pile)

Max Activating Token Index: 43