Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 261 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1117319 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1551788 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1015100 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1412193 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0418. Min Act: -0.0004

Data Index: 1232097 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1392965 (Python Code)

Max Activating Token Index: 802

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0411. Min Act: 0.0000

Data Index: 1573510 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1533428 (Python Code)

Max Activating Token Index: 799

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1511646 (Python Code)

Max Activating Token Index: 530

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1563721 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1570436 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1546399 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0004

Data Index: 1191680 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0373. Min Act: -0.0004

Data Index: 1020735 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1016151 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0381. Min Act: -0.0003

Data Index: 81150 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0360. Min Act: -0.0003

Data Index: 869581 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1430194 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1583699 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1383292 (Python Code)

Max Activating Token Index: 987