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

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

Neuron 356 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0993. Min Act: -0.0001

Data Index: 178622 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0958. Min Act: -0.0001

Data Index: 577311 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.1036. Min Act: -0.0001

Data Index: 262155 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0976. Min Act: -0.0001

Data Index: 958884 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0819. Min Act: -0.0001

Data Index: 673009 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1135852 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1109919 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0769. Min Act: -0.0001

Data Index: 539889 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0856. Min Act: -0.0001

Data Index: 988995 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0866. Min Act: -0.0001

Data Index: 422380 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0783. Min Act: -0.0001

Data Index: 57775 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0711. Min Act: -0.0001

Data Index: 342164 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0772. Min Act: -0.0001

Data Index: 803829 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0721. Min Act: -0.0001

Data Index: 25895 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0767. Min Act: -0.0001

Data Index: 821758 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0729. Min Act: -0.0000

Data Index: 849013 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0742. Min Act: -0.0001

Data Index: 55418 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0739. Min Act: -0.0001

Data Index: 513494 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0740. Min Act: -0.0001

Data Index: 815467 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0771. Min Act: -0.0001

Data Index: 120558 (C4 (Web Text))

Max Activating Token Index: 891