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

Dataset: The Pile

Neuron 176 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2034. Min Act: -0.0000

Data Index: 200446 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1964. Min Act: -0.0000

Data Index: 181767 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1891. Min Act: -0.0000

Data Index: 696475 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1742. Min Act: -0.0000

Data Index: 206277 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1753. Min Act: -0.0000

Data Index: 313273 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1774476 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1666270 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1779735 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1757018 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1112385 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1004082 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1587. Min Act: -0.0000

Data Index: 94936 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1812. Min Act: -0.0000

Data Index: 770187 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1553. Min Act: -0.0000

Data Index: 133966 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1512. Min Act: -0.0000

Data Index: 447252 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1526185 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1698. Min Act: -0.0000

Data Index: 194230 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1472884 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1300112 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1741. Min Act: -0.0000

Data Index: 196168 (The Pile)

Max Activating Token Index: 553