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

Dataset: The Pile

Neuron 148 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1724646 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1377522 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2979. Min Act: -0.0000

Data Index: 489107 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2743. Min Act: -0.0000

Data Index: 263723 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2633. Min Act: -0.0000

Data Index: 114064 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1962329 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1381500 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2116. Min Act: -0.0000

Data Index: 127389 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1414098 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1645143 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1849. Min Act: -0.0000

Data Index: 327929 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1396168 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1498655 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2305. Min Act: -0.0000

Data Index: 722014 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1861. Min Act: -0.0000

Data Index: 327435 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1495. Min Act: -0.0000

Data Index: 865073 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1444013 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1741. Min Act: -0.0000

Data Index: 612431 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1014436 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1601546 (The Pile)

Max Activating Token Index: 27