Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 357 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1510078 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.2388. Min Act: -0.0000

Data Index: 275840 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0343. Min Act: -0.0000

Data Index: 917725 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9856. Min Act: -0.0000

Data Index: 906316 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1350. Min Act: -0.0000

Data Index: 820588 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1543185 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1632985 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1498281 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1603033 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1373945 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1560086 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1396914 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8229. Min Act: -0.0000

Data Index: 836378 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1524405 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8341. Min Act: -0.0000

Data Index: 960961 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1637375 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8001. Min Act: -0.0000

Data Index: 613480 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1551306 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.7473. Min Act: -0.0000

Data Index: 342645 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.7434. Min Act: -0.0000

Data Index: 599858 (C4 (Web Text))

Max Activating Token Index: 314