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

Dataset: The Pile

Neuron 471 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1522966 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1756872 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1374089 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1099466 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8701. Min Act: -0.0000

Data Index: 964041 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1990735 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1218709 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1385310 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8650. Min Act: -0.0000

Data Index: 841129 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1499605 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1063108 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8225. Min Act: -0.0000

Data Index: 920987 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1591130 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1326120 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7457. Min Act: -0.0000

Data Index: 122608 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1270218 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1992351 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7732. Min Act: -0.0000

Data Index: 789449 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7684. Min Act: -0.0000

Data Index: 777958 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1960372 (The Pile)

Max Activating Token Index: 967