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

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

Neuron 3600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0528. Min Act: -0.0002

Data Index: 246218 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0002

Data Index: 354489 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0623. Min Act: -0.0002

Data Index: 73933 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0489. Min Act: -0.0002

Data Index: 183375 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1608 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1070750 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0517. Min Act: -0.0002

Data Index: 777443 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0480. Min Act: -0.0002

Data Index: 824574 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0545. Min Act: -0.0002

Data Index: 237330 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0512. Min Act: -0.0002

Data Index: 6596 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0430. Min Act: -0.0002

Data Index: 584537 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0431. Min Act: -0.0002

Data Index: 323587 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0465. Min Act: -0.0002

Data Index: 107567 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1060311 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0494. Min Act: -0.0002

Data Index: 716765 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0556. Min Act: -0.0002

Data Index: 894910 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0475. Min Act: -0.0002

Data Index: 167318 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0402. Min Act: -0.0002

Data Index: 210161 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1016542 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0461. Min Act: -0.0002

Data Index: 19557 (C4 (Web Text))

Max Activating Token Index: 210