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

Dataset: The Pile

Neuron 1243 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: 1.4068. Min Range: -1.4068

Max Act: 1.4068. Min Act: -0.0000

Data Index: 148923 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1975264 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1621758 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.2215. Min Act: 0.0000

Data Index: 698521 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1267634 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1838050 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1798046 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.2585. Min Act: -0.0000

Data Index: 887396 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1141410 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1496206 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1556. Min Act: -0.0000

Data Index: 588971 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1457213 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0932. Min Act: -0.0000

Data Index: 375703 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1955589 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1866530 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0837. Min Act: 0.0000

Data Index: 241816 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0675. Min Act: -0.0000

Data Index: 552765 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1514757 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1988829 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0392. Min Act: 0.0000

Data Index: 660218 (The Pile)

Max Activating Token Index: 94