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

Dataset: The Pile

Neuron 5068 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1233266 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1358383 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8006. Min Act: -0.0000

Data Index: 857480 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1179159 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1475498 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7409. Min Act: -0.0000

Data Index: 504620 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7670. Min Act: -0.0000

Data Index: 707594 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1917 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1285700 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6752. Min Act: -0.0000

Data Index: 861830 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6604. Min Act: -0.0000

Data Index: 613332 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7012. Min Act: -0.0000

Data Index: 453460 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6678. Min Act: -0.0000

Data Index: 360947 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1241496 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6461. Min Act: -0.0000

Data Index: 368022 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6637. Min Act: -0.0000

Data Index: 320997 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5812. Min Act: -0.0000

Data Index: 973915 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6165. Min Act: -0.0000

Data Index: 892678 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6294. Min Act: -0.0000

Data Index: 157409 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6422. Min Act: -0.0000

Data Index: 155119 (The Pile)

Max Activating Token Index: 227