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

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

Neuron 2355 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1102385 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1073. Min Act: -0.0001

Data Index: 72750 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1034. Min Act: -0.0001

Data Index: 108571 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0881. Min Act: -0.0001

Data Index: 429062 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1030. Min Act: -0.0001

Data Index: 42412 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1278151 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1374620 (Python Code)

Max Activating Token Index: 634

Text #7

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1054. Min Act: -0.0001

Data Index: 82217 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1014. Min Act: -0.0001

Data Index: 781992 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1014. Min Act: -0.0001

Data Index: 281598 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1086. Min Act: -0.0001

Data Index: 787529 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1079290 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1241811 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1029430 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1012. Min Act: -0.0001

Data Index: 115130 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0934. Min Act: -0.0001

Data Index: 924741 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1004077 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0905. Min Act: -0.0001

Data Index: 638130 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0915. Min Act: -0.0001

Data Index: 177720 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1283852 (C4 (Web Text))

Max Activating Token Index: 443