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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 190 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5762. Min Act: -0.0000

Data Index: 667750 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5256. Min Act: -0.0000

Data Index: 251807 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5057. Min Act: -0.0000

Data Index: 52181 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4555. Min Act: 0.0000

Data Index: 837106 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4516. Min Act: -0.0000

Data Index: 895653 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4434. Min Act: -0.0000

Data Index: 285114 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4609. Min Act: 0.0000

Data Index: 276673 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4309. Min Act: -0.0000

Data Index: 914724 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4535. Min Act: -0.0000

Data Index: 413567 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4342. Min Act: -0.0000

Data Index: 666231 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4076. Min Act: 0.0000

Data Index: 740318 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4112. Min Act: -0.0000

Data Index: 416060 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4398. Min Act: 0.0000

Data Index: 239581 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4420. Min Act: -0.0000

Data Index: 879699 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4201. Min Act: -0.0000

Data Index: 241238 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1336159 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3988. Min Act: -0.0000

Data Index: 599936 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3816. Min Act: -0.0000

Data Index: 527401 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4635. Min Act: -0.0000

Data Index: 422350 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1058286 (C4 (Web Text))

Max Activating Token Index: 784