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

Dataset: The Pile

Neuron 2528 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: 0.8065. Min Range: -0.8065

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1897625 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1395409 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1347409 (The Pile)

Max Activating Token Index: 843

Text #3

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7812. Min Act: -0.0000

Data Index: 428665 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1914448 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1192042 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6884. Min Act: -0.0000

Data Index: 87329 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7066. Min Act: -0.0000

Data Index: 386872 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6917. Min Act: -0.0000

Data Index: 635976 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6656. Min Act: -0.0000

Data Index: 340372 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7083. Min Act: -0.0000

Data Index: 440453 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1436958 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6365. Min Act: -0.0000

Data Index: 361500 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6127. Min Act: -0.0000

Data Index: 560933 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6581. Min Act: -0.0000

Data Index: 457997 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1055645 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1108050 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5921. Min Act: -0.0000

Data Index: 14368 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5712. Min Act: -0.0000

Data Index: 516207 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1369111 (The Pile)

Max Activating Token Index: 1003