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

Dataset: The Pile

Neuron 686 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: 0.8760. Min Range: -0.8760

Max Act: 0.8760. Min Act: -0.0000

Data Index: 956313 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1139456 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1753111 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6732. Min Act: -0.0000

Data Index: 846723 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5994. Min Act: -0.0000

Data Index: 112082 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1934209 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5891. Min Act: -0.0000

Data Index: 953510 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1649604 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1412189 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6201. Min Act: -0.0000

Data Index: 610115 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5568. Min Act: -0.0000

Data Index: 984519 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1347135 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1729136 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5260. Min Act: -0.0000

Data Index: 798453 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1459452 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5360. Min Act: 0.0000

Data Index: 257505 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5162. Min Act: 0.0000

Data Index: 1867912 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.4975. Min Act: 0.0000

Data Index: 322048 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.4721. Min Act: -0.0000

Data Index: 60132 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.4893. Min Act: -0.0000

Data Index: 373729 (The Pile)

Max Activating Token Index: 1017