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

Dataset: The Pile

Neuron 3153 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: 0.5428. Min Range: -0.5428

Max Act: 0.5404. Min Act: -0.0001

Data Index: 119882 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1498264 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0000

Data Index: 32578 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5068. Min Act: -0.0000

Data Index: 115164 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1921320 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4859. Min Act: -0.0000

Data Index: 201542 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4677. Min Act: -0.0000

Data Index: 773677 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1333106 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4706. Min Act: -0.0000

Data Index: 379505 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4249. Min Act: -0.0000

Data Index: 754152 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4366. Min Act: -0.0000

Data Index: 657597 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4697. Min Act: -0.0000

Data Index: 67723 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4612. Min Act: -0.0000

Data Index: 964943 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1440563 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1219142 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1315082 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1975858 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1418696 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4358. Min Act: -0.0000

Data Index: 404976 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4476. Min Act: -0.0000

Data Index: 776284 (The Pile)

Max Activating Token Index: 775