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

Dataset: The Pile

Neuron 308 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: 0.0000

Data Index: 7308 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1441. Min Act: 0.0000

Data Index: 1413634 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1260. Min Act: 0.0000

Data Index: 1537452 (The Pile)

Max Activating Token Index: 932

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1159049 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1152. Min Act: -0.0000

Data Index: 155356 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1207. Min Act: 0.0000

Data Index: 13133 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1100. Min Act: -0.0000

Data Index: 664221 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1515604 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1053. Min Act: 0.0000

Data Index: 1529293 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1740939 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1364399 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1029997 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1024. Min Act: 0.0000

Data Index: 1732118 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1046. Min Act: 0.0000

Data Index: 278557 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1055. Min Act: -0.0000

Data Index: 912647 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1021. Min Act: -0.0000

Data Index: 683005 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0984. Min Act: 0.0000

Data Index: 764255 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1452318 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0999. Min Act: 0.0000

Data Index: 219422 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1586999 (The Pile)

Max Activating Token Index: 869