Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1781740 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2987. Min Act: -0.0000

Data Index: 898193 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2659. Min Act: -0.0000

Data Index: 848856 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1443519 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1550431 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2467. Min Act: -0.0000

Data Index: 398907 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2287. Min Act: -0.0000

Data Index: 973846 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2360. Min Act: -0.0000

Data Index: 391594 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1507038 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1360554 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1768006 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2080. Min Act: -0.0000

Data Index: 577746 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2372. Min Act: -0.0000

Data Index: 13941 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1416930 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2265. Min Act: -0.0000

Data Index: 120596 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2211. Min Act: -0.0000

Data Index: 272874 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2152. Min Act: -0.0000

Data Index: 232694 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1802186 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1855584 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1159059 (The Pile)

Max Activating Token Index: 903