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

Dataset: The Pile

Neuron 4909 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.9501. Min Act: -0.0000

Data Index: 1287220 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.8648. Min Act: -0.0000

Data Index: 378236 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1372251 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1626968 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.7606. Min Act: -0.0000

Data Index: 224547 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.6364. Min Act: -0.0000

Data Index: 179189 (The Pile)

Max Activating Token Index: 581

Text #6

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.6735. Min Act: -0.0000

Data Index: 1022124 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.6592. Min Act: -0.0000

Data Index: 1596271 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1455139 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.5614. Min Act: -0.0000

Data Index: 88430 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.2982. Min Act: -0.0000

Data Index: 978592 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.2004. Min Act: -0.0000

Data Index: 805446 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.1894. Min Act: -0.0000

Data Index: 8823 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1455241 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.1824. Min Act: -0.0000

Data Index: 292357 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.2222. Min Act: -0.0000

Data Index: 877977 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.2942. Min Act: -0.0000

Data Index: 316994 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.1888. Min Act: -0.0000

Data Index: 558453 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.2172. Min Act: -0.0000

Data Index: 462129 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.9501. Min Range: -1.9501

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1565889 (The Pile)

Max Activating Token Index: 813