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

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

Neuron 5036 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: 0.7741. Min Range: -0.7741

Max Act: 0.7612. Min Act: -0.0001

Data Index: 828593 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7741. Min Act: -0.0001

Data Index: 794709 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7037. Min Act: -0.0001

Data Index: 1064619 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6777. Min Act: -0.0001

Data Index: 1201403 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6769. Min Act: -0.0001

Data Index: 424855 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7093. Min Act: -0.0001

Data Index: 935614 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6187. Min Act: -0.0001

Data Index: 1225104 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6221. Min Act: -0.0001

Data Index: 224773 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6618. Min Act: -0.0001

Data Index: 1151252 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6404. Min Act: -0.0001

Data Index: 516565 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5911. Min Act: -0.0001

Data Index: 247851 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1279538 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6482. Min Act: -0.0001

Data Index: 7329 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6439. Min Act: -0.0001

Data Index: 1046005 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5918. Min Act: -0.0001

Data Index: 1030449 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6070. Min Act: -0.0001

Data Index: 343766 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6174. Min Act: -0.0001

Data Index: 99271 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6234. Min Act: -0.0001

Data Index: 640109 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5984. Min Act: -0.0001

Data Index: 901421 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6191. Min Act: -0.0001

Data Index: 934390 (C4 (Web Text))

Max Activating Token Index: 842