Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1328 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0003

Data Index: 188529 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1496591 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0394. Min Act: -0.0003

Data Index: 184472 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1155517 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1469970 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1618517 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0396. Min Act: -0.0003

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1590420 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0391. Min Act: -0.0003

Data Index: 531710 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1446419 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0381. Min Act: -0.0003

Data Index: 610168 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1492987 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0385. Min Act: -0.0003

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1386676 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1241119 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1453028 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0380. Min Act: -0.0003

Data Index: 899468 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1032568 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1519614 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1381136 (Python Code)

Max Activating Token Index: 635