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

Dataset: The Pile

Neuron 5113 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: 4.5843. Min Range: -4.5843

Max Act: 4.5843. Min Act: -0.0000

Data Index: 1359440 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.6489. Min Act: -0.0000

Data Index: 145876 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.7705. Min Act: -0.0000

Data Index: 1648258 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.5178. Min Act: -0.0000

Data Index: 1720176 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.7605. Min Act: -0.0000

Data Index: 742009 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.4843. Min Act: -0.0000

Data Index: 1551946 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.4453. Min Act: -0.0000

Data Index: 175130 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.4246. Min Act: -0.0000

Data Index: 1802702 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.2267. Min Act: -0.0000

Data Index: 458353 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.2094. Min Act: -0.0000

Data Index: 950769 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.2767. Min Act: -0.0000

Data Index: 1425881 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.2177. Min Act: -0.0000

Data Index: 802657 (The Pile)

Max Activating Token Index: 940

Text #12

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.2237. Min Act: -0.0000

Data Index: 185712 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.1744. Min Act: -0.0000

Data Index: 1068599 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 4.5843. Min Range: -4.5843

Max Act: 2.9974. Min Act: -0.0000

Data Index: 1563517 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.1511. Min Act: -0.0000

Data Index: 1163128 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 4.5843. Min Range: -4.5843

Max Act: 2.9792. Min Act: -0.0000

Data Index: 1238082 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 4.5843. Min Range: -4.5843

Max Act: 2.9659. Min Act: -0.0000

Data Index: 991095 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.0811. Min Act: -0.0000

Data Index: 1773599 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 4.5843. Min Range: -4.5843

Max Act: 3.2374. Min Act: -0.0000

Data Index: 1331585 (The Pile)

Max Activating Token Index: 279