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

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

Neuron 1814 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: 1.2426. Min Range: -1.2426

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1376506 (Python Code)

Max Activating Token Index: 545

Text #1

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1462. Min Act: -0.0000

Data Index: 349735 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1304. Min Act: 0.0000

Data Index: 438823 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1505. Min Act: -0.0000

Data Index: 465976 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0789. Min Act: 0.0000

Data Index: 1356890 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1548751 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1517382 (Python Code)

Max Activating Token Index: 173

Text #7

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1344. Min Act: 0.0000

Data Index: 84018 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1609315 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1456526 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1252951 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1638481 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1421333 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1639304 (Python Code)

Max Activating Token Index: 1021

Text #14

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1394700 (Python Code)

Max Activating Token Index: 687

Text #15

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1491049 (Python Code)

Max Activating Token Index: 131

Text #16

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0679. Min Act: -0.0000

Data Index: 595252 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1473084 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0620. Min Act: 0.0000

Data Index: 1170800 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1373899 (Python Code)

Max Activating Token Index: 751