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

Dataset: The Pile

Neuron 2817 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: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0000

Data Index: 943629 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1096. Min Act: -0.0000

Data Index: 125773 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1283110 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1069. Min Act: -0.0000

Data Index: 477457 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1033. Min Act: 0.0000

Data Index: 1816105 (The Pile)

Max Activating Token Index: 41

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1033. Min Act: -0.0000

Data Index: 896493 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1449437 (The Pile)

Max Activating Token Index: 51

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1016. Min Act: -0.0000

Data Index: 838552 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1015. Min Act: -0.0000

Data Index: 231743 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1009. Min Act: -0.0000

Data Index: 813528 (The Pile)

Max Activating Token Index: 2

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1007. Min Act: 0.0000

Data Index: 43965 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0997. Min Act: 0.0000

Data Index: 659502 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0995. Min Act: -0.0000

Data Index: 81743 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0978. Min Act: -0.0000

Data Index: 929561 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1313236 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0958. Min Act: -0.0000

Data Index: 510616 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1268534 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0949. Min Act: 0.0000

Data Index: 673141 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1288935 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0937. Min Act: 0.0000

Data Index: 396427 (The Pile)

Max Activating Token Index: 924