Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2122 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1436562 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1371978 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1613543 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1512570 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1518637 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1572516 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1496368 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1463031 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1521381 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1360669 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1642974 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1372182 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1502377 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1627319 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1609936 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1513185 (Python Code)

Max Activating Token Index: 413

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1524332 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1652478 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1409273 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1476410 (Python Code)

Max Activating Token Index: 898