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

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

Neuron 185 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.6716. Min Act: -0.0000

Data Index: 84666 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.1894. Min Act: -0.0000

Data Index: 866070 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.2065. Min Act: -0.0001

Data Index: 531456 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.2073. Min Act: -0.0000

Data Index: 965546 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.9603. Min Act: -0.0000

Data Index: 809584 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1054484 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.2233. Min Act: -0.0000

Data Index: 1085310 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.9711. Min Act: -0.0000

Data Index: 1118214 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.0332. Min Act: -0.0000

Data Index: 1568210 (Python Code)

Max Activating Token Index: 742

Text #9

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.0333. Min Act: -0.0000

Data Index: 559163 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.1067. Min Act: -0.0000

Data Index: 711838 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.8914. Min Act: -0.0000

Data Index: 1654044 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 2.6716. Min Range: -2.6716

Max Act: 2.0494. Min Act: -0.0000

Data Index: 195424 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.7702. Min Act: -0.0000

Data Index: 809985 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.6984. Min Act: -0.0000

Data Index: 635517 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.8202. Min Act: -0.0000

Data Index: 767632 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.7517. Min Act: -0.0001

Data Index: 689142 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1039269 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.5904. Min Act: -0.0000

Data Index: 412393 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 2.6716. Min Range: -2.6716

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1186850 (C4 (Web Text))

Max Activating Token Index: 222