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

Dataset: The Pile

Neuron 1853 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1757853 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.6761. Min Act: -0.0000

Data Index: 1843874 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.5240. Min Act: -0.0000

Data Index: 333878 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.4537. Min Act: -0.0000

Data Index: 8607 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.4545. Min Act: -0.0000

Data Index: 189099 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1568811 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1166038 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.3011. Min Act: -0.0000

Data Index: 1356046 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.3800. Min Act: -0.0000

Data Index: 951067 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.2756. Min Act: -0.0000

Data Index: 627436 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1391302 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1038169 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1193469 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.2247. Min Act: -0.0000

Data Index: 69896 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1901138 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1871934 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1478727 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1174263 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 1.6761. Min Range: -1.6761

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1085791 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 1.6761. Min Range: -1.6761

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1497176 (The Pile)

Max Activating Token Index: 1000