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

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

Neuron 4288 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1372216 (Python Code)

Max Activating Token Index: 338

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1601962 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1433757 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1423995 (Python Code)

Max Activating Token Index: 319

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1434315 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1607493 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1403208 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1613348 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1491445 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1468267 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1635069 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1527993 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1535550 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1549247 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1628369 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1535285 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1385632 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1600631 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1603279 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1503893 (Python Code)

Max Activating Token Index: 705