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

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

Neuron 306 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: 0.6361. Min Range: -0.6361

Max Act: 0.6361. Min Act: -0.0000

Data Index: 194931 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.6022. Min Act: -0.0000

Data Index: 169626 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.5678. Min Act: -0.0000

Data Index: 934927 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.5299. Min Act: -0.0000

Data Index: 138866 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.5039. Min Act: -0.0000

Data Index: 344825 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4916. Min Act: -0.0000

Data Index: 466916 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1138546 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4889. Min Act: -0.0000

Data Index: 769155 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4551. Min Act: -0.0000

Data Index: 276106 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4472. Min Act: -0.0000

Data Index: 577498 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4623. Min Act: -0.0000

Data Index: 206512 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4616. Min Act: -0.0000

Data Index: 505170 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1070412 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4569. Min Act: -0.0000

Data Index: 522425 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4546. Min Act: -0.0000

Data Index: 587320 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1332925 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4458. Min Act: -0.0000

Data Index: 284721 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4410. Min Act: -0.0000

Data Index: 582350 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4347. Min Act: -0.0000

Data Index: 392237 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.6361. Min Range: -0.6361

Max Act: 0.4289. Min Act: -0.0000

Data Index: 211125 (C4 (Web Text))

Max Activating Token Index: 730