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

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

Neuron 3184 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0035. Min Act: -0.0001

Data Index: 337722 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0001

Data Index: 1186541 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0001

Data Index: 90984 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0028. Min Act: -0.0001

Data Index: 305940 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0027. Min Act: -0.0001

Data Index: 1157184 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0029. Min Act: -0.0001

Data Index: 801446 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0027. Min Act: -0.0001

Data Index: 1311491 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0027. Min Act: -0.0001

Data Index: 1284608 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0027. Min Act: -0.0001

Data Index: 1039098 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0024. Min Act: -0.0001

Data Index: 288391 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0001

Data Index: 424882 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0001

Data Index: 82930 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1349942 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0024. Min Act: -0.0001

Data Index: 1273820 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1329589 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0027. Min Act: -0.0001

Data Index: 486082 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0001

Data Index: 272794 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0001

Data Index: 920817 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0001

Data Index: 1235074 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0001

Data Index: 310553 (C4 (Web Text))

Max Activating Token Index: 228