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

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

Neuron 3302 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1516. Min Range: -3.1516

Max Act: 3.0987. Min Act: -0.0000

Data Index: 1186701 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.9167. Min Act: -0.0001

Data Index: 469647 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 3.1516. Min Range: -3.1516

Max Act: 3.1516. Min Act: -0.0001

Data Index: 187550 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.6217. Min Act: -0.0001

Data Index: 43125 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.4613. Min Act: -0.0000

Data Index: 852803 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.5701. Min Act: -0.0001

Data Index: 115562 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.5549. Min Act: -0.0001

Data Index: 75308 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.4122. Min Act: -0.0001

Data Index: 879897 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.6817. Min Act: -0.0001

Data Index: 1045978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.4689. Min Act: -0.0000

Data Index: 261505 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.3674. Min Act: -0.0000

Data Index: 1029614 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.4700. Min Act: -0.0000

Data Index: 282475 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.4288. Min Act: -0.0001

Data Index: 1109512 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.3569. Min Act: -0.0001

Data Index: 207757 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.3344. Min Act: -0.0001

Data Index: 1080424 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.1916. Min Act: -0.0001

Data Index: 1350927 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.3096. Min Act: -0.0001

Data Index: 94781 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1320708 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.3149. Min Act: -0.0001

Data Index: 6870 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 3.1516. Min Range: -3.1516

Max Act: 2.1742. Min Act: -0.0001

Data Index: 355292 (C4 (Web Text))

Max Activating Token Index: 344