Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 333 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.3098. Min Act: -0.0000

Data Index: 575584 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.3821. Min Act: -0.0000

Data Index: 1793597 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.2889. Min Act: -0.0000

Data Index: 281930 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.2501. Min Act: -0.0000

Data Index: 76482 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.2825. Min Act: -0.0000

Data Index: 168203 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1754117 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1967. Min Act: -0.0000

Data Index: 707947 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1908589 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1226310 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1369153 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1996. Min Act: -0.0000

Data Index: 790495 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1930546 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1356. Min Act: -0.0000

Data Index: 362020 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.0905. Min Act: -0.0000

Data Index: 418441 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1564282 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1816044 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1702345 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1172. Min Act: -0.0000

Data Index: 33127 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.0817. Min Act: -0.0000

Data Index: 761382 (The Pile)

Max Activating Token Index: 864

Text #19

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1552627 (The Pile)

Max Activating Token Index: 832