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

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

Neuron 3865 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: 0.7379. Min Range: -0.7379

Max Act: 0.6996. Min Act: -0.0000

Data Index: 737718 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.7379. Min Act: -0.0000

Data Index: 791378 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1392060 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1128160 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1439213 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5421. Min Act: -0.0000

Data Index: 972441 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1646964 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1424836 (Python Code)

Max Activating Token Index: 51

Text #8

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.6848. Min Act: -0.0000

Data Index: 257680 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5741. Min Act: -0.0000

Data Index: 568996 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5851. Min Act: -0.0000

Data Index: 14493 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1562528 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5394. Min Act: -0.0000

Data Index: 746580 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5120. Min Act: -0.0000

Data Index: 22489 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5652. Min Act: -0.0000

Data Index: 414339 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5259. Min Act: -0.0000

Data Index: 101449 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.4857. Min Act: -0.0000

Data Index: 442656 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.5082. Min Act: -0.0000

Data Index: 696972 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1393102 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.7379. Min Range: -0.7379

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1365765 (Python Code)

Max Activating Token Index: 506