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

Dataset: The Pile

Neuron 3460 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1004489 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1026045 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1302. Min Act: 0.0000

Data Index: 995219 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1167. Min Act: 0.0000

Data Index: 951368 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1113. Min Act: 0.0000

Data Index: 1453477 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1113. Min Act: 0.0000

Data Index: 517254 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1153. Min Act: 0.0000

Data Index: 956544 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1132. Min Act: -0.0000

Data Index: 673335 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1111. Min Act: 0.0000

Data Index: 1786283 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1070. Min Act: 0.0000

Data Index: 1980629 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1105. Min Act: 0.0000

Data Index: 442774 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1064. Min Act: 0.0000

Data Index: 630075 (The Pile)

Max Activating Token Index: 5

Text #12

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0985. Min Act: 0.0000

Data Index: 1099317 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0979. Min Act: -0.0000

Data Index: 413795 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0967. Min Act: 0.0000

Data Index: 1470611 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0987. Min Act: 0.0000

Data Index: 610452 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0949. Min Act: 0.0000

Data Index: 816199 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0940. Min Act: 0.0000

Data Index: 1434564 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1834864 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0940. Min Act: 0.0000

Data Index: 1529270 (The Pile)

Max Activating Token Index: 2