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

Dataset: The Pile

Neuron 179 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: 0.1166. Min Range: -0.1166

Max Act: 0.1166. Min Act: 0.0000

Data Index: 576274 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0787. Min Act: 0.0000

Data Index: 714564 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0679. Min Act: -0.0000

Data Index: 946864 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1521996 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0657. Min Act: 0.0000

Data Index: 564784 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0607. Min Act: 0.0000

Data Index: 275904 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0582. Min Act: 0.0000

Data Index: 199908 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0524. Min Act: 0.0000

Data Index: 1333714 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0516. Min Act: 0.0000

Data Index: 840838 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0514. Min Act: -0.0000

Data Index: 130260 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1500547 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1570338 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0495. Min Act: 0.0000

Data Index: 1075046 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0487. Min Act: 0.0000

Data Index: 1196928 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0486. Min Act: -0.0000

Data Index: 173237 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1117015 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0486. Min Act: 0.0000

Data Index: 176711 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0478. Min Act: 0.0000

Data Index: 1722997 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0477. Min Act: 0.0000

Data Index: 752805 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0475. Min Act: 0.0000

Data Index: 301206 (The Pile)

Max Activating Token Index: 1023