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

Dataset: The Pile

Neuron 2128 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: 0.3621. Min Range: -0.3621

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1632336 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3238. Min Act: -0.0000

Data Index: 754474 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1699797 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2603. Min Act: -0.0000

Data Index: 589902 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2661. Min Act: -0.0000

Data Index: 462782 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1821781 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1137106 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1919310 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2503. Min Act: -0.0000

Data Index: 217189 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1155788 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2377. Min Act: -0.0000

Data Index: 337955 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1820774 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1272656 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1041017 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2296. Min Act: -0.0000

Data Index: 615546 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2178. Min Act: -0.0000

Data Index: 561820 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1689869 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2100. Min Act: -0.0000

Data Index: 984879 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1662280 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2042. Min Act: -0.0000

Data Index: 435036 (The Pile)

Max Activating Token Index: 107