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

Dataset: The Pile

Neuron 2776 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: 0.1182. Min Range: -0.1182

Max Act: 0.1155. Min Act: -0.0000

Data Index: 74789 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1571006 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1374730 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1138. Min Act: 0.0000

Data Index: 928327 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1137. Min Act: 0.0000

Data Index: 1587843 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1077. Min Act: -0.0000

Data Index: 894283 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1074802 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1100723 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1664144 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1936040 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0967. Min Act: -0.0000

Data Index: 751002 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0950. Min Act: -0.0000

Data Index: 352937 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0950. Min Act: -0.0000

Data Index: 55986 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1949089 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0965. Min Act: 0.0000

Data Index: 1637745 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1484478 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1321556 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0869. Min Act: -0.0000

Data Index: 523120 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0855. Min Act: -0.0000

Data Index: 251034 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1004710 (The Pile)

Max Activating Token Index: 6