Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1562 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0001

Data Index: 933471 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0626. Min Act: -0.0001

Data Index: 470219 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0626. Min Act: -0.0001

Data Index: 794485 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1297062 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0578. Min Act: -0.0001

Data Index: 581427 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0556. Min Act: -0.0001

Data Index: 326345 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1310124 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0597. Min Act: -0.0001

Data Index: 756433 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0551. Min Act: -0.0001

Data Index: 304937 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0567. Min Act: -0.0001

Data Index: 340870 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1047448 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0579. Min Act: -0.0001

Data Index: 98741 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1123412 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0568. Min Act: -0.0001

Data Index: 586262 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0539. Min Act: -0.0001

Data Index: 699370 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1077564 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0574. Min Act: -0.0001

Data Index: 511477 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0555. Min Act: -0.0001

Data Index: 209046 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0534. Min Act: -0.0001

Data Index: 220984 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1047963 (C4 (Web Text))

Max Activating Token Index: 574