Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1123460 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1151. Min Act: -0.0001

Data Index: 131542 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1021. Min Act: -0.0001

Data Index: 726297 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1342057 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1059440 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1343537 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0849. Min Act: -0.0001

Data Index: 59795 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0873. Min Act: -0.0001

Data Index: 965017 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0908. Min Act: -0.0002

Data Index: 668865 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0827. Min Act: -0.0001

Data Index: 638333 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0811. Min Act: -0.0002

Data Index: 904755 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0826. Min Act: -0.0001

Data Index: 871743 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0800. Min Act: -0.0002

Data Index: 3400 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0828. Min Act: -0.0001

Data Index: 656378 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0857. Min Act: -0.0001

Data Index: 259543 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1169172 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0842. Min Act: -0.0001

Data Index: 287803 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0814. Min Act: -0.0001

Data Index: 760056 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0823. Min Act: -0.0001

Data Index: 11574 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1206267 (C4 (Web Text))

Max Activating Token Index: 897