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

Dataset: The Pile

Neuron 3797 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1531959 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1574752 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1030525 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1389357 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1527301 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1802951 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1796. Min Act: -0.0000

Data Index: 443475 (The Pile)

Max Activating Token Index: 688

Text #7

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1841597 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1796. Min Act: -0.0000

Data Index: 501481 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1520332 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1364054 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1275367 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1752. Min Act: -0.0000

Data Index: 343445 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1693. Min Act: -0.0000

Data Index: 464342 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1639035 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1926808 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1907774 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1687624 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1592. Min Act: -0.0000

Data Index: 53415 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1848707 (The Pile)

Max Activating Token Index: 42