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

Dataset: The Pile

Neuron 2800 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: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0000

Data Index: 766704 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1007. Min Act: -0.0000

Data Index: 563238 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1168194 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1167952 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1981330 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1823813 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0953. Min Act: -0.0000

Data Index: 753297 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1548168 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0948. Min Act: -0.0000

Data Index: 656729 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1015262 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0975. Min Act: -0.0000

Data Index: 542617 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1170060 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0939. Min Act: -0.0000

Data Index: 796546 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1485201 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1092063 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0971. Min Act: -0.0000

Data Index: 169141 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0935. Min Act: -0.0000

Data Index: 159320 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1012977 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0933. Min Act: -0.0000

Data Index: 415729 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1649587 (The Pile)

Max Activating Token Index: 299