Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5358 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.2081. Min Range: -6.2081

Max Act: 6.2081. Min Act: -0.0000

Data Index: 1223581 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.9786. Min Act: -0.0000

Data Index: 272097 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.8223. Min Act: -0.0000

Data Index: 1103334 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.2799. Min Act: -0.0000

Data Index: 1044741 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.6017. Min Act: -0.0000

Data Index: 304124 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.3732. Min Act: -0.0000

Data Index: 446725 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.2056. Min Act: -0.0000

Data Index: 532873 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.3219. Min Act: -0.0000

Data Index: 957637 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.4455. Min Act: -0.0000

Data Index: 189156 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.5558. Min Act: -0.0001

Data Index: 675831 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.6532. Min Act: -0.0000

Data Index: 560861 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.0717. Min Act: -0.0001

Data Index: 110342 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 6.2081. Min Range: -6.2081

Max Act: 4.8669. Min Act: -0.0001

Data Index: 313037 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 6.2081. Min Range: -6.2081

Max Act: 4.7866. Min Act: -0.0000

Data Index: 1183880 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 6.2081. Min Range: -6.2081

Max Act: 4.9629. Min Act: -0.0000

Data Index: 1129180 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.0849. Min Act: -0.0000

Data Index: 1349699 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 6.2081. Min Range: -6.2081

Max Act: 5.0175. Min Act: -0.0000

Data Index: 986667 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 6.2081. Min Range: -6.2081

Max Act: 4.4898. Min Act: -0.0000

Data Index: 1086837 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 6.2081. Min Range: -6.2081

Max Act: 4.7930. Min Act: -0.0000

Data Index: 160926 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 6.2081. Min Range: -6.2081

Max Act: 4.6124. Min Act: -0.0000

Data Index: 462766 (C4 (Web Text))

Max Activating Token Index: 186