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

Dataset: The Pile

Neuron 3958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1307041 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1969795 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1561203 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1614. Min Act: -0.0000

Data Index: 992179 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1771. Min Act: -0.0000

Data Index: 485743 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1542967 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1576403 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1873250 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0496. Min Act: -0.0000

Data Index: 891174 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0819. Min Act: -0.0000

Data Index: 758809 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0602. Min Act: -0.0000

Data Index: 542372 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1405. Min Act: -0.0000

Data Index: 363160 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0500. Min Act: -0.0000

Data Index: 267834 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1039956 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0688. Min Act: -0.0000

Data Index: 742232 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1265099 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1849340 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1336425 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0204. Min Act: -0.0000

Data Index: 919606 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9979. Min Act: -0.0000

Data Index: 650932 (The Pile)

Max Activating Token Index: 819