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

Dataset: The Pile

Neuron 364 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: 1.0211. Min Range: -1.0211

Max Act: 1.0211. Min Act: -0.0000

Data Index: 937691 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.0211. Min Range: -1.0211

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1583694 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 1.0211. Min Range: -1.0211

Max Act: 1.0008. Min Act: -0.0000

Data Index: 535102 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 1.0211. Min Range: -1.0211

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1628064 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.0211. Min Range: -1.0211

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1557485 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9798. Min Act: -0.0000

Data Index: 728686 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1110316 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1977020 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9429. Min Act: -0.0000

Data Index: 551507 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1462272 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1017314 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9801. Min Act: -0.0000

Data Index: 740388 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9733. Min Act: -0.0000

Data Index: 465809 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1500860 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9108. Min Act: -0.0000

Data Index: 29786 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9363. Min Act: -0.0000

Data Index: 859116 (The Pile)

Max Activating Token Index: 718

Text #16

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9253. Min Act: -0.0000

Data Index: 174908 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9687. Min Act: -0.0000

Data Index: 277546 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1869593 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1052421 (The Pile)

Max Activating Token Index: 736