Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.8087. Min Act: -0.0000

Data Index: 258380 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1519375 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.3683. Min Act: -0.0000

Data Index: 987168 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2962. Min Act: -0.0000

Data Index: 73681 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2100. Min Act: -0.0000

Data Index: 149035 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1346913 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1869. Min Act: -0.0000

Data Index: 316714 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2094. Min Act: -0.0000

Data Index: 743635 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1028977 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1923409 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2312. Min Act: -0.0000

Data Index: 103131 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1798. Min Act: -0.0000

Data Index: 953114 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1612418 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2251. Min Act: -0.0000

Data Index: 723988 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1433099 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1172560 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0971. Min Act: -0.0000

Data Index: 667068 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1175. Min Act: -0.0000

Data Index: 637073 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1334177 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2063. Min Act: -0.0000

Data Index: 548105 (The Pile)

Max Activating Token Index: 580