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

Dataset: The Pile

Neuron 4713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8815. Min Act: -0.0000

Data Index: 596000 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9029. Min Act: -0.0000

Data Index: 401851 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1832958 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1386382 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1034446 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8039. Min Act: -0.0000

Data Index: 379605 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8482. Min Act: -0.0000

Data Index: 252574 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7465. Min Act: -0.0000

Data Index: 323670 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7914. Min Act: -0.0000

Data Index: 501689 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1213363 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1783177 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7234. Min Act: -0.0000

Data Index: 177891 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1386271 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8085. Min Act: -0.0000

Data Index: 380778 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7828. Min Act: -0.0000

Data Index: 929790 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1337627 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1487564 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7225. Min Act: -0.0000

Data Index: 406842 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7641. Min Act: -0.0000

Data Index: 333920 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1773196 (The Pile)

Max Activating Token Index: 107