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

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

Neuron 5032 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: 0.1219. Min Range: -0.1219

Max Act: 0.1203. Min Act: -0.0001

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1168. Min Act: -0.0000

Data Index: 306376 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1505410 (Python Code)

Max Activating Token Index: 474

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0001

Data Index: 768197 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1046. Min Act: -0.0000

Data Index: 145237 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0919. Min Act: -0.0001

Data Index: 528909 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0892. Min Act: -0.0000

Data Index: 981812 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1287535 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0921. Min Act: -0.0001

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1094202 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1130156 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0803. Min Act: -0.0001

Data Index: 102312 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1202235 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0749. Min Act: -0.0001

Data Index: 942567 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0831. Min Act: -0.0001

Data Index: 235142 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0818. Min Act: -0.0001

Data Index: 248509 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0790. Min Act: -0.0001

Data Index: 175174 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0732. Min Act: -0.0001

Data Index: 667993 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0833. Min Act: -0.0001

Data Index: 385120 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1142066 (C4 (Web Text))

Max Activating Token Index: 374