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

Dataset: The Pile

Neuron 4513 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: 4.0865. Min Range: -4.0865

Max Act: 4.0865. Min Act: -0.0000

Data Index: 1121132 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.7579. Min Act: -0.0000

Data Index: 249946 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.7768. Min Act: -0.0000

Data Index: 1881132 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.4867. Min Act: -0.0000

Data Index: 594923 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.5346. Min Act: -0.0000

Data Index: 1417661 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.6678. Min Act: -0.0000

Data Index: 1985334 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.8182. Min Act: -0.0000

Data Index: 215941 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.5251. Min Act: -0.0000

Data Index: 918994 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.2329. Min Act: -0.0000

Data Index: 1301868 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.4419. Min Act: -0.0000

Data Index: 1592106 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.1201. Min Act: -0.0000

Data Index: 46075 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.3030. Min Act: -0.0000

Data Index: 1108990 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.6706. Min Act: -0.0000

Data Index: 352896 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.6713. Min Act: -0.0000

Data Index: 316103 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.4440. Min Act: -0.0000

Data Index: 83533 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 4.0865. Min Range: -4.0865

Max Act: 2.8870. Min Act: -0.0000

Data Index: 627666 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.4949. Min Act: -0.0000

Data Index: 1323135 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 4.0865. Min Range: -4.0865

Max Act: 2.9960. Min Act: -0.0000

Data Index: 1560667 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 4.0865. Min Range: -4.0865

Max Act: 2.8547. Min Act: -0.0000

Data Index: 144284 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 4.0865. Min Range: -4.0865

Max Act: 3.0885. Min Act: -0.0000

Data Index: 973024 (The Pile)

Max Activating Token Index: 42