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

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

Neuron 450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1451291 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1446313 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1497161 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1575957 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1481260 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1382974 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1492917 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1391134 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1604013 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1519309 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1607376 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1492820 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1504939 (Python Code)

Max Activating Token Index: 925

Text #13

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7872. Min Act: -0.0000

Data Index: 661105 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1550434 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1552315 (Python Code)

Max Activating Token Index: 634

Text #16

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1398511 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1653560 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1611342 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1635247 (Python Code)

Max Activating Token Index: 792