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

Dataset: The Pile

Neuron 3721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.2663. Min Act: -0.0000

Data Index: 92835 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.1019. Min Act: -0.0000

Data Index: 470022 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.2238. Min Act: -0.0000

Data Index: 954191 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1296854 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.0343. Min Act: -0.0000

Data Index: 281926 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.0178. Min Act: -0.0000

Data Index: 363863 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1090029 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 1.2663. Min Range: -1.2663

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1592224 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.8741. Min Act: -0.0000

Data Index: 898261 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.7861. Min Act: -0.0000

Data Index: 156567 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.9973. Min Act: -0.0000

Data Index: 849273 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1070855 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1391697 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1122668 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1455908 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1861848 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.7932. Min Act: -0.0000

Data Index: 378049 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.8750. Min Act: -0.0000

Data Index: 441295 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1628993 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 1.2663. Min Range: -1.2663

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1068133 (The Pile)

Max Activating Token Index: 169