Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 706 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1077. Min Act: -0.0002

Data Index: 187566 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0997. Min Act: -0.0002

Data Index: 423768 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1008. Min Act: -0.0002

Data Index: 511234 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0963. Min Act: -0.0002

Data Index: 910133 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1333681 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0940. Min Act: -0.0002

Data Index: 46118 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1185716 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0917. Min Act: -0.0002

Data Index: 958345 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0931. Min Act: -0.0002

Data Index: 274334 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1187040 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1317500 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0876. Min Act: -0.0002

Data Index: 318237 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0868. Min Act: -0.0002

Data Index: 583836 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0830. Min Act: -0.0002

Data Index: 366243 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0873. Min Act: -0.0002

Data Index: 84756 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0844. Min Act: -0.0002

Data Index: 969837 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0856. Min Act: -0.0002

Data Index: 613542 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0815. Min Act: -0.0002

Data Index: 610448 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1037407 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0811. Min Act: -0.0002

Data Index: 786829 (C4 (Web Text))

Max Activating Token Index: 79