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

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

Neuron 2256 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: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1135634 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0694. Min Act: -0.0001

Data Index: 574707 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0602. Min Act: -0.0001

Data Index: 282985 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0565. Min Act: -0.0001

Data Index: 980624 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1287510 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0551. Min Act: -0.0001

Data Index: 929768 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0513. Min Act: -0.0001

Data Index: 896659 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1524781 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1516168 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1386036 (Python Code)

Max Activating Token Index: 184

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1560007 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1486977 (Python Code)

Max Activating Token Index: 791

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1538127 (Python Code)

Max Activating Token Index: 229

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1640762 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0527. Min Act: -0.0001

Data Index: 163946 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0505. Min Act: -0.0001

Data Index: 863676 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1549968 (Python Code)

Max Activating Token Index: 226

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1150228 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1008738 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1451478 (Python Code)

Max Activating Token Index: 892