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

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

Neuron 3556 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: 0.9738. Min Range: -0.9738

Max Act: 0.8250. Min Act: -0.0002

Data Index: 440890 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.8753. Min Act: -0.0002

Data Index: 920614 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.9738. Min Act: -0.0002

Data Index: 807776 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.7377. Min Act: -0.0002

Data Index: 179677 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6965. Min Act: -0.0002

Data Index: 346793 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6715. Min Act: -0.0002

Data Index: 476254 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.7032. Min Act: -0.0002

Data Index: 390581 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6976. Min Act: -0.0002

Data Index: 405066 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6965. Min Act: -0.0002

Data Index: 1107091 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6511. Min Act: -0.0002

Data Index: 10558 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6733. Min Act: -0.0002

Data Index: 1349316 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.7095. Min Act: -0.0002

Data Index: 748869 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6370. Min Act: -0.0002

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6635. Min Act: -0.0002

Data Index: 583710 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6551. Min Act: -0.0002

Data Index: 447822 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6449. Min Act: -0.0002

Data Index: 1148166 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6629. Min Act: -0.0002

Data Index: 714237 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.5333. Min Act: -0.0002

Data Index: 688776 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.6052. Min Act: -0.0002

Data Index: 915871 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.9738. Min Range: -0.9738

Max Act: 0.5818. Min Act: -0.0002

Data Index: 955589 (C4 (Web Text))

Max Activating Token Index: 587