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

Dataset: The Pile

Neuron 2932 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: 5.5245. Min Range: -5.5245

Max Act: 5.4354. Min Act: -0.0000

Data Index: 1206797 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.0368. Min Act: -0.0000

Data Index: 39926 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.5245. Min Act: -0.0000

Data Index: 1637141 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.4538. Min Act: -0.0000

Data Index: 1091082 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.4184. Min Act: -0.0000

Data Index: 1804146 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.0187. Min Act: -0.0000

Data Index: 216361 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.0705. Min Act: -0.0000

Data Index: 1970747 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.4209. Min Act: -0.0000

Data Index: 704908 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.2770. Min Act: -0.0000

Data Index: 1380418 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 5.5245. Min Range: -5.5245

Max Act: 4.8622. Min Act: -0.0000

Data Index: 1095295 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.3994. Min Act: -0.0000

Data Index: 1826514 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 5.5245. Min Range: -5.5245

Max Act: 4.8245. Min Act: -0.0000

Data Index: 1027266 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 5.5245. Min Range: -5.5245

Max Act: 4.9562. Min Act: -0.0000

Data Index: 1658774 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.2925. Min Act: -0.0000

Data Index: 1795450 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.2767. Min Act: -0.0000

Data Index: 1845142 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 5.5245. Min Range: -5.5245

Max Act: 4.9366. Min Act: -0.0000

Data Index: 71049 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.0780. Min Act: -0.0000

Data Index: 1513701 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 5.5245. Min Range: -5.5245

Max Act: 4.8680. Min Act: -0.0000

Data Index: 1138578 (The Pile)

Max Activating Token Index: 28

Text #18

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.0484. Min Act: -0.0000

Data Index: 1632737 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 5.5245. Min Range: -5.5245

Max Act: 5.2034. Min Act: -0.0000

Data Index: 1831374 (The Pile)

Max Activating Token Index: 50