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

Dataset: The Pile

Neuron 1133 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: 0.7735. Min Range: -0.7735

Max Act: 0.7735. Min Act: -0.0000

Data Index: 466456 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1193455 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6509. Min Act: -0.0000

Data Index: 536971 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1672639 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1607845 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5971. Min Act: -0.0000

Data Index: 812072 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5877. Min Act: -0.0000

Data Index: 713180 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1652001 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5943. Min Act: -0.0000

Data Index: 663499 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1564113 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1528052 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1587723 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1127661 (The Pile)

Max Activating Token Index: 769

Text #13

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5296. Min Act: -0.0000

Data Index: 471453 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1445715 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1596539 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1115861 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5281. Min Act: -0.0000

Data Index: 139732 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5248. Min Act: -0.0000

Data Index: 416766 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1209947 (The Pile)

Max Activating Token Index: 816