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

Dataset: The Pile

Neuron 2608 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: 0.1078. Min Range: -0.1078

Max Act: 0.1074. Min Act: 0.0000

Data Index: 1306843 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0000

Data Index: 659352 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1073. Min Act: -0.0000

Data Index: 313961 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1003. Min Act: -0.0000

Data Index: 692050 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0985. Min Act: 0.0000

Data Index: 238385 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1200653 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1119927 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0938. Min Act: 0.0000

Data Index: 1906064 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0940. Min Act: 0.0000

Data Index: 565987 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0936. Min Act: 0.0000

Data Index: 899392 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0932. Min Act: -0.0000

Data Index: 413393 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0929. Min Act: 0.0000

Data Index: 282323 (The Pile)

Max Activating Token Index: 5

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0931. Min Act: -0.0000

Data Index: 705559 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0924. Min Act: -0.0000

Data Index: 133245 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0922. Min Act: -0.0000

Data Index: 602267 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1336869 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1301127 (The Pile)

Max Activating Token Index: 2

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0944. Min Act: 0.0001

Data Index: 1627473 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0905. Min Act: -0.0000

Data Index: 661096 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1225237 (The Pile)

Max Activating Token Index: 14