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

Dataset: The Pile

Neuron 3557 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: 0.8896. Min Range: -0.8896

Max Act: 0.8816. Min Act: -0.0000

Data Index: 975530 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.8896. Min Act: -0.0000

Data Index: 964997 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7930. Min Act: -0.0000

Data Index: 412043 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1122798 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1172764 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7390. Min Act: -0.0000

Data Index: 290714 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1759246 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1119714 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1376977 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6231. Min Act: -0.0000

Data Index: 50204 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6140. Min Act: -0.0000

Data Index: 747959 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6227. Min Act: -0.0000

Data Index: 198787 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1302555 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5863. Min Act: -0.0000

Data Index: 802015 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6032. Min Act: -0.0000

Data Index: 651895 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1555596 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6298. Min Act: -0.0000

Data Index: 328938 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1049404 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1430996 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5609. Min Act: -0.0000

Data Index: 489254 (The Pile)

Max Activating Token Index: 281