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

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

Neuron 219 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1384463 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0446. Min Act: -0.0002

Data Index: 809344 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1387890 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1431100 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1655345 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1579266 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1456410 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0420. Min Act: -0.0003

Data Index: 614081 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1559366 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1401668 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0418. Min Act: -0.0003

Data Index: 253138 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1108724 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1461633 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0417. Min Act: -0.0003

Data Index: 797118 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1009585 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1525765 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0401. Min Act: -0.0003

Data Index: 337564 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0400. Min Act: -0.0002

Data Index: 561364 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1607847 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0394. Min Act: -0.0002

Data Index: 822919 (C4 (Web Text))

Max Activating Token Index: 695