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

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

Neuron 279 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.6030. Min Act: -0.0000

Data Index: 577430 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4721. Min Act: -0.0000

Data Index: 561641 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4625. Min Act: -0.0000

Data Index: 645925 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1066330 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4156. Min Act: -0.0000

Data Index: 904520 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4509. Min Act: -0.0000

Data Index: 399929 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4012. Min Act: -0.0000

Data Index: 375052 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4016. Min Act: -0.0000

Data Index: 585621 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3969. Min Act: -0.0000

Data Index: 46600 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4037. Min Act: -0.0000

Data Index: 11912 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4295. Min Act: -0.0000

Data Index: 683900 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.4013. Min Act: -0.0001

Data Index: 603734 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1252118 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1137936 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3712. Min Act: -0.0000

Data Index: 897111 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3658. Min Act: -0.0000

Data Index: 685695 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3674. Min Act: -0.0000

Data Index: 98759 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3414. Min Act: -0.0000

Data Index: 932129 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.3618. Min Act: -0.0000

Data Index: 872890 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.6030. Min Range: -0.6030

Max Act: 0.2687. Min Act: -0.0000

Data Index: 246242 (C4 (Web Text))

Max Activating Token Index: 300