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

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

Neuron 5569 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: 3.1319. Min Range: -3.1319

Max Act: 3.1319. Min Act: -0.0000

Data Index: 41107 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 3.1319. Min Range: -3.1319

Max Act: 2.4621. Min Act: -0.0000

Data Index: 1327267 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 3.1319. Min Range: -3.1319

Max Act: 2.3610. Min Act: -0.0000

Data Index: 131965 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 3.1319. Min Range: -3.1319

Max Act: 2.1722. Min Act: -0.0000

Data Index: 505723 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.1319. Min Range: -3.1319

Max Act: 2.0073. Min Act: -0.0000

Data Index: 749727 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1582000 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9609. Min Act: -0.0000

Data Index: 620537 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9499. Min Act: -0.0000

Data Index: 207037 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.8412. Min Act: -0.0000

Data Index: 1089347 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9260. Min Act: -0.0000

Data Index: 677700 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9138. Min Act: -0.0000

Data Index: 548519 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1287335 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.9187. Min Act: -0.0000

Data Index: 1615474 (Python Code)

Max Activating Token Index: 202

Text #13

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1050342 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.8971. Min Act: -0.0000

Data Index: 685445 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1022090 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.8500. Min Act: -0.0000

Data Index: 381700 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.8379. Min Act: -0.0000

Data Index: 1028330 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.7300. Min Act: -0.0000

Data Index: 543348 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.1319. Min Range: -3.1319

Max Act: 1.6189. Min Act: -0.0000

Data Index: 940666 (C4 (Web Text))

Max Activating Token Index: 972