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

Dataset: The Pile

Neuron 3871 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2053. Min Range: -1.2053

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1846426 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 1.2053. Min Range: -1.2053

Max Act: 1.1011. Min Act: -0.0000

Data Index: 295860 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9412. Min Act: -0.0000

Data Index: 589150 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1386727 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1570420 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1495045 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1798393 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1910236 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1933466 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1156768 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1844884 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1978676 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8373. Min Act: -0.0000

Data Index: 459848 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8723. Min Act: -0.0000

Data Index: 482677 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8440. Min Act: -0.0000

Data Index: 600228 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1251717 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1642700 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1115715 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1489082 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1673817 (The Pile)

Max Activating Token Index: 490