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

Dataset: The Pile

Neuron 1908 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: 2.0017. Min Range: -2.0017

Max Act: 2.0017. Min Act: -0.0000

Data Index: 1781404 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.9705. Min Act: -0.0000

Data Index: 1729236 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1622870 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1728675 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.6500. Min Act: -0.0000

Data Index: 409843 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8420. Min Act: -0.0000

Data Index: 879784 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8176. Min Act: -0.0000

Data Index: 718361 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.4087. Min Act: -0.0000

Data Index: 669601 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.7302. Min Act: -0.0000

Data Index: 994649 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.6252. Min Act: -0.0000

Data Index: 815092 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.5912. Min Act: -0.0000

Data Index: 1419772 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.7852. Min Act: -0.0000

Data Index: 390084 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.4883. Min Act: -0.0000

Data Index: 323837 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.4884. Min Act: -0.0000

Data Index: 465224 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1909057 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1800494 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.5883. Min Act: -0.0000

Data Index: 1884525 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.7036. Min Act: -0.0000

Data Index: 1763365 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.4205. Min Act: -0.0000

Data Index: 652482 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1016702 (The Pile)

Max Activating Token Index: 977