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

Dataset: The Pile

Neuron 2098 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: 0.9339. Min Range: -0.9339

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1078147 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9251. Min Act: -0.0000

Data Index: 602462 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1830480 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8853. Min Act: -0.0000

Data Index: 929015 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9183. Min Act: -0.0000

Data Index: 580626 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8971. Min Act: -0.0000

Data Index: 24072 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8360. Min Act: -0.0000

Data Index: 958110 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1492607 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8322. Min Act: -0.0000

Data Index: 256195 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7988. Min Act: -0.0000

Data Index: 939452 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8231. Min Act: -0.0000

Data Index: 826512 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8530. Min Act: -0.0000

Data Index: 97733 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7943. Min Act: -0.0000

Data Index: 598585 (The Pile)

Max Activating Token Index: 324

Text #13

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8037. Min Act: -0.0000

Data Index: 251237 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1815445 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1196010 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7839. Min Act: -0.0000

Data Index: 97098 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7831. Min Act: -0.0000

Data Index: 283017 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7578. Min Act: -0.0000

Data Index: 207956 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7753. Min Act: -0.0000

Data Index: 758283 (The Pile)

Max Activating Token Index: 155