Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2865 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.7220. Min Act: -0.0000

Data Index: 926111 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.7263. Min Act: -0.0000

Data Index: 698801 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1399957 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1005166 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1921283 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1355631 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5695. Min Act: -0.0000

Data Index: 558556 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1732581 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5712. Min Act: -0.0000

Data Index: 567866 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1204556 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4923. Min Act: -0.0000

Data Index: 181116 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4953. Min Act: -0.0000

Data Index: 321238 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5132. Min Act: -0.0000

Data Index: 142403 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1224677 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1791186 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5578. Min Act: -0.0000

Data Index: 873903 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5192. Min Act: -0.0000

Data Index: 602509 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1265718 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5113. Min Act: -0.0000

Data Index: 746003 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4926. Min Act: -0.0000

Data Index: 647148 (The Pile)

Max Activating Token Index: 595