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

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

Neuron 4881 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1301372 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1125108 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1390371 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1471810 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1572531 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1548960 (Python Code)

Max Activating Token Index: 777

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1430503 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1499579 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1411395 (Python Code)

Max Activating Token Index: 614

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1389871 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1625090 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1566729 (Python Code)

Max Activating Token Index: 685

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1503226 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1565253 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1636079 (Python Code)

Max Activating Token Index: 358

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1577225 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1422072 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1496314 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1373776 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1600731 (Python Code)

Max Activating Token Index: 445