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

Dataset: The Pile

Neuron 4073 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: 7.7878. Min Range: -7.7878

Max Act: 7.7878. Min Act: -0.0000

Data Index: 777870 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 7.7878. Min Range: -7.7878

Max Act: 6.6170. Min Act: -0.0000

Data Index: 1550800 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 7.7878. Min Range: -7.7878

Max Act: 6.5052. Min Act: -0.0000

Data Index: 1333112 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 7.7878. Min Range: -7.7878

Max Act: 6.2987. Min Act: -0.0000

Data Index: 338230 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 7.7878. Min Range: -7.7878

Max Act: 6.2717. Min Act: -0.0000

Data Index: 1666536 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 7.7878. Min Range: -7.7878

Max Act: 6.0389. Min Act: -0.0000

Data Index: 1147305 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.9815. Min Act: -0.0000

Data Index: 667398 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 7.7878. Min Range: -7.7878

Max Act: 6.1204. Min Act: -0.0000

Data Index: 1141156 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.6159. Min Act: -0.0000

Data Index: 789076 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.6090. Min Act: -0.0000

Data Index: 1453144 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.9407. Min Act: -0.0000

Data Index: 1433396 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.9444. Min Act: -0.0000

Data Index: 356100 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.7418. Min Act: -0.0000

Data Index: 822688 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.5071. Min Act: -0.0000

Data Index: 1489046 (The Pile)

Max Activating Token Index: 288

Text #14

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.3558. Min Act: -0.0000

Data Index: 1072546 (The Pile)

Max Activating Token Index: 900

Text #15

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.5346. Min Act: -0.0000

Data Index: 692995 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.6805. Min Act: -0.0000

Data Index: 233976 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.0002. Min Act: -0.0000

Data Index: 1290581 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.1837. Min Act: -0.0000

Data Index: 79784 (The Pile)

Max Activating Token Index: 427

Text #19

Max Range: 7.7878. Min Range: -7.7878

Max Act: 5.5510. Min Act: -0.0000

Data Index: 941735 (The Pile)

Max Activating Token Index: 28