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

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

Neuron 3285 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: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0001

Data Index: 925151 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0637. Min Act: -0.0000

Data Index: 391701 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0597. Min Act: -0.0001

Data Index: 838491 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0609. Min Act: -0.0000

Data Index: 215376 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0602. Min Act: -0.0001

Data Index: 651008 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0592. Min Act: -0.0000

Data Index: 27799 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1432978 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0594. Min Act: -0.0001

Data Index: 72692 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0559. Min Act: -0.0001

Data Index: 689228 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1237687 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1159006 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1003902 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0488. Min Act: -0.0001

Data Index: 866693 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1025367 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1075750 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0519. Min Act: -0.0001

Data Index: 996507 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0507. Min Act: -0.0000

Data Index: 744210 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0486. Min Act: -0.0001

Data Index: 774951 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1223445 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1169478 (C4 (Web Text))

Max Activating Token Index: 774