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

Dataset: The Pile

Neuron 2570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.8757. Min Act: -0.0000

Data Index: 1133020 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.9494. Min Act: -0.0000

Data Index: 112638 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 3.1106. Min Range: -3.1106

Max Act: 3.1106. Min Act: 0.0000

Data Index: 210986 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.9117. Min Act: -0.0000

Data Index: 1367723 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.9000. Min Act: -0.0000

Data Index: 734158 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.8447. Min Act: -0.0000

Data Index: 1350363 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.7256. Min Act: -0.0000

Data Index: 216872 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 3.1106. Min Range: -3.1106

Max Act: 3.0071. Min Act: 0.0000

Data Index: 1585613 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.6808. Min Act: -0.0000

Data Index: 1909698 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.8066. Min Act: -0.0000

Data Index: 1588879 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.7973. Min Act: -0.0000

Data Index: 358445 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.7939. Min Act: -0.0000

Data Index: 1009901 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.8028. Min Act: 0.0000

Data Index: 1910834 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.7954. Min Act: 0.0000

Data Index: 1487433 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.7597. Min Act: -0.0000

Data Index: 799756 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.6059. Min Act: -0.0000

Data Index: 1829204 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.8497. Min Act: -0.0000

Data Index: 872610 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.5724. Min Act: -0.0000

Data Index: 1944680 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.5720. Min Act: -0.0000

Data Index: 1354974 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 3.1106. Min Range: -3.1106

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1690069 (The Pile)

Max Activating Token Index: 659