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

Dataset: The Pile

Neuron 2007 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: 1.0475. Min Range: -1.0475

Max Act: 0.9901. Min Act: -0.0000

Data Index: 635398 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1950319 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1695602 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1914091 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9436. Min Act: -0.0000

Data Index: 406790 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8518. Min Act: -0.0000

Data Index: 973737 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1991126 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1886864 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9734. Min Act: -0.0000

Data Index: 126867 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1083890 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9138. Min Act: -0.0000

Data Index: 330752 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9152. Min Act: -0.0000

Data Index: 802215 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1392371 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1096818 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8842. Min Act: -0.0000

Data Index: 920679 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1678530 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1527478 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1915476 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1016449 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1632586 (The Pile)

Max Activating Token Index: 306