Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6062 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7496. Min Act: -0.0000

Data Index: 438901 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7139. Min Act: -0.0000

Data Index: 131600 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6704. Min Act: -0.0000

Data Index: 701401 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1225441 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1358370 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6388. Min Act: -0.0000

Data Index: 236310 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5777. Min Act: -0.0000

Data Index: 634940 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5843. Min Act: -0.0000

Data Index: 954910 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1643062 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6132. Min Act: -0.0000

Data Index: 447083 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6289. Min Act: -0.0000

Data Index: 681165 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6273. Min Act: -0.0000

Data Index: 136983 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5675. Min Act: -0.0000

Data Index: 243875 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6031. Min Act: -0.0000

Data Index: 875587 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1428903 (Python Code)

Max Activating Token Index: 908

Text #16

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5614. Min Act: -0.0000

Data Index: 396716 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5672. Min Act: -0.0000

Data Index: 659162 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1330223 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5425. Min Act: -0.0000

Data Index: 517049 (C4 (Web Text))

Max Activating Token Index: 156