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

Dataset: The Pile

Neuron 579 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1239940 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1037150 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.1772. Min Act: -0.0000

Data Index: 254918 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1835242 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.1106. Min Act: -0.0000

Data Index: 261370 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1684139 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1909609 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1281919 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0876. Min Act: -0.0000

Data Index: 919596 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1288243 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1963086 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1971387 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1175242 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9448. Min Act: -0.0000

Data Index: 455835 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9825. Min Act: -0.0000

Data Index: 483235 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0229. Min Act: -0.0000

Data Index: 585027 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1190894 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.1772. Min Range: -1.1772

Max Act: 1.0770. Min Act: -0.0000

Data Index: 701509 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9250. Min Act: -0.0000

Data Index: 601705 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.1772. Min Range: -1.1772

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1080071 (The Pile)

Max Activating Token Index: 317