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

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

Neuron 4430 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: 0.1131. Min Range: -0.1131

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1013654 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0990. Min Act: -0.0001

Data Index: 557599 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: -0.0001

Data Index: 213809 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1028647 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1039405 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1179141 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0814. Min Act: -0.0001

Data Index: 963323 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0809. Min Act: -0.0001

Data Index: 212991 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0816. Min Act: -0.0001

Data Index: 888194 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0736. Min Act: -0.0001

Data Index: 232610 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1012747 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1565744 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0746. Min Act: -0.0001

Data Index: 161239 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0674. Min Act: -0.0001

Data Index: 354893 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0676. Min Act: -0.0001

Data Index: 461991 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1358888 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0741. Min Act: -0.0001

Data Index: 59127 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0715. Min Act: -0.0001

Data Index: 850929 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0706. Min Act: -0.0001

Data Index: 18245 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1647300 (Python Code)

Max Activating Token Index: 267