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

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

Neuron 2212 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1324190 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.7490. Min Act: -0.0000

Data Index: 147798 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1650785 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1605289 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1509263 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1436198 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6211. Min Act: -0.0000

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1454284 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1482132 (Python Code)

Max Activating Token Index: 396

Text #9

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1245281 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6548. Min Act: -0.0000

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6183. Min Act: -0.0000

Data Index: 773675 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1177396 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1385550 (Python Code)

Max Activating Token Index: 885

Text #14

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5625. Min Act: -0.0000

Data Index: 297645 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6663. Min Act: -0.0000

Data Index: 115482 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1137033 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1431089 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6178. Min Act: -0.0000

Data Index: 464003 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1477739 (Python Code)

Max Activating Token Index: 677