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

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

Neuron 4574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5680. Min Act: -0.0000

Data Index: 524645 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5664. Min Act: -0.0000

Data Index: 320510 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5195. Min Act: -0.0000

Data Index: 43731 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5201. Min Act: -0.0000

Data Index: 188982 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1008408 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5074. Min Act: -0.0000

Data Index: 194884 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1344844 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4805. Min Act: -0.0000

Data Index: 358178 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4748. Min Act: -0.0000

Data Index: 527574 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1130009 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4782. Min Act: -0.0000

Data Index: 444876 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5075. Min Act: -0.0000

Data Index: 333572 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1034690 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5024. Min Act: -0.0000

Data Index: 547508 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1011958 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4550. Min Act: -0.0000

Data Index: 594231 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4777. Min Act: -0.0000

Data Index: 520258 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4586. Min Act: -0.0000

Data Index: 414139 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4444. Min Act: -0.0000

Data Index: 598482 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1095017 (C4 (Web Text))

Max Activating Token Index: 951