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

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

Neuron 5009 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: 3.2789. Min Range: -3.2789

Max Act: 3.2789. Min Act: -0.0001

Data Index: 560945 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.7719. Min Act: -0.0000

Data Index: 1196242 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.6780. Min Act: -0.0001

Data Index: 1136127 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.6987. Min Act: -0.0000

Data Index: 26322 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.6385. Min Act: -0.0001

Data Index: 644057 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.6920. Min Act: -0.0001

Data Index: 712434 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.6418. Min Act: -0.0001

Data Index: 320403 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.5629. Min Act: -0.0000

Data Index: 63443 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.4808. Min Act: -0.0000

Data Index: 1225328 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.6074. Min Act: -0.0001

Data Index: 257121 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.5065. Min Act: -0.0000

Data Index: 1059690 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.5016. Min Act: -0.0001

Data Index: 462568 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.4466. Min Act: -0.0001

Data Index: 1046934 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.4238. Min Act: -0.0000

Data Index: 545646 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.4336. Min Act: -0.0001

Data Index: 395213 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.3106. Min Act: -0.0001

Data Index: 1287274 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.5212. Min Act: -0.0000

Data Index: 394978 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.5433. Min Act: -0.0001

Data Index: 66645 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.4110. Min Act: -0.0001

Data Index: 121942 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 3.2789. Min Range: -3.2789

Max Act: 2.4664. Min Act: -0.0000

Data Index: 85348 (C4 (Web Text))

Max Activating Token Index: 174