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

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

Neuron 1952 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: 0.0521. Min Range: -0.0521

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1434570 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1085997 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1388966 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1496678 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1591571 (Python Code)

Max Activating Token Index: 794

Text #5

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1470651 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1426183 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1426034 (Python Code)

Max Activating Token Index: 951

Text #8

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1293048 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0424. Min Act: -0.0003

Data Index: 685418 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1331444 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0421. Min Act: -0.0003

Data Index: 655502 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1545017 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0401. Min Act: -0.0003

Data Index: 201216 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0416. Min Act: -0.0003

Data Index: 453945 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0401. Min Act: -0.0003

Data Index: 744508 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1640120 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1620015 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1634919 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0398. Min Act: -0.0003

Data Index: 375171 (C4 (Web Text))

Max Activating Token Index: 899