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

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

Neuron 1320 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1492767 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1438864 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1582570 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1603853 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1551608 (Python Code)

Max Activating Token Index: 968

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1394410 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1592443 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1582562 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1526935 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1598039 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1482579 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1467269 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1483626 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1550498 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1472829 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1520199 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1431608 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1489932 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1641305 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1623079 (Python Code)

Max Activating Token Index: 503