Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1037 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0004

Data Index: 1425028 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0431. Min Act: -0.0004

Data Index: 1460041 (Python Code)

Max Activating Token Index: 354

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0429. Min Act: -0.0004

Data Index: 1511273 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0387. Min Act: -0.0004

Data Index: 1405471 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0385. Min Act: -0.0004

Data Index: 1440402 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0380. Min Act: -0.0004

Data Index: 1592802 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1522662 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0390. Min Act: -0.0004

Data Index: 1401200 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1338776 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0402. Min Act: -0.0004

Data Index: 1404997 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0418. Min Act: -0.0004

Data Index: 1607226 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0400. Min Act: -0.0004

Data Index: 1618985 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0400. Min Act: -0.0004

Data Index: 1545010 (Python Code)

Max Activating Token Index: 946

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0415. Min Act: -0.0004

Data Index: 1465254 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0379. Min Act: -0.0004

Data Index: 1542346 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1463892 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1548325 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0392. Min Act: -0.0004

Data Index: 1411756 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1489800 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0391. Min Act: -0.0004

Data Index: 1558769 (Python Code)

Max Activating Token Index: 207