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

Dataset: The Pile

Neuron 3580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.7069. Min Act: -0.0000

Data Index: 1743333 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.9410. Min Act: -0.0000

Data Index: 420452 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5459. Min Act: -0.0000

Data Index: 85098 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4374. Min Act: -0.0000

Data Index: 770896 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1346071 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1454137 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4216. Min Act: -0.0000

Data Index: 198558 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4878. Min Act: -0.0000

Data Index: 980824 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1014231 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1044153 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1549527 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3203. Min Act: -0.0000

Data Index: 685906 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.1729. Min Act: -0.0000

Data Index: 455167 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.1926. Min Act: -0.0000

Data Index: 753294 (The Pile)

Max Activating Token Index: 81

Text #14

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1104511 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2269. Min Act: -0.0000

Data Index: 509542 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1398633 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2878. Min Act: -0.0000

Data Index: 364788 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.1683. Min Act: -0.0000

Data Index: 182325 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3609. Min Act: -0.0000

Data Index: 226734 (The Pile)

Max Activating Token Index: 785