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

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

Neuron 2306 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7618. Min Act: -0.0001

Data Index: 254148 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6358. Min Act: -0.0001

Data Index: 350486 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7622. Min Act: -0.0000

Data Index: 596920 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7912. Min Act: -0.0001

Data Index: 851236 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7086. Min Act: -0.0001

Data Index: 978797 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1228116 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1126369 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7550. Min Act: -0.0001

Data Index: 735044 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7574. Min Act: -0.0001

Data Index: 603910 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7473. Min Act: -0.0001

Data Index: 394330 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1145449 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.5427. Min Act: -0.0001

Data Index: 164984 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7583. Min Act: -0.0001

Data Index: 1171982 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1029693 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6472. Min Act: -0.0000

Data Index: 565016 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6778. Min Act: -0.0000

Data Index: 710954 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1053405 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6976. Min Act: -0.0000

Data Index: 585118 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1059481 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6866. Min Act: -0.0000

Data Index: 830788 (C4 (Web Text))

Max Activating Token Index: 1010