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

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

Neuron 1343 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.3822. Min Act: -0.0001

Data Index: 1437123 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.0137. Min Act: -0.0000

Data Index: 758194 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9742. Min Act: -0.0001

Data Index: 1644636 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9103. Min Act: -0.0001

Data Index: 942048 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9611. Min Act: -0.0000

Data Index: 935145 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9787. Min Act: -0.0001

Data Index: 1534134 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9117. Min Act: -0.0001

Data Index: 456460 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9050. Min Act: -0.0000

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1641310 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8264. Min Act: -0.0001

Data Index: 845213 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1073543 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8619. Min Act: -0.0000

Data Index: 889656 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9056. Min Act: -0.0000

Data Index: 599459 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9047. Min Act: -0.0001

Data Index: 556221 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9301. Min Act: -0.0001

Data Index: 1638229 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8517. Min Act: -0.0000

Data Index: 975381 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8768. Min Act: -0.0000

Data Index: 645237 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8726. Min Act: -0.0000

Data Index: 945917 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8746. Min Act: -0.0000

Data Index: 513331 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.8420. Min Act: -0.0000

Data Index: 212454 (C4 (Web Text))

Max Activating Token Index: 394