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

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

Neuron 1512 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1608989 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5880. Min Act: -0.0001

Data Index: 1608473 (Python Code)

Max Activating Token Index: 781

Text #2

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5725. Min Act: -0.0001

Data Index: 1479211 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5231. Min Act: -0.0000

Data Index: 149073 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5014. Min Act: -0.0001

Data Index: 477387 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4711. Min Act: -0.0001

Data Index: 1220266 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1080021 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4522. Min Act: -0.0001

Data Index: 1640599 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4673. Min Act: -0.0000

Data Index: 464799 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4592. Min Act: -0.0000

Data Index: 922562 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4486. Min Act: -0.0000

Data Index: 215170 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4452. Min Act: -0.0001

Data Index: 80265 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4616. Min Act: -0.0000

Data Index: 500203 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1189904 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4675. Min Act: -0.0001

Data Index: 1310030 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4311. Min Act: -0.0000

Data Index: 319188 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1603514 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1615012 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1225213 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1401565 (Python Code)

Max Activating Token Index: 407