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

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

Neuron 2710 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: 0.1506. Min Range: -0.1506

Max Act: 0.1484. Min Act: -0.0003

Data Index: 1484327 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1408. Min Act: -0.0003

Data Index: 1451224 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1375. Min Act: -0.0003

Data Index: 1635357 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1417. Min Act: -0.0003

Data Index: 1502241 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0003

Data Index: 1583079 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1353. Min Act: -0.0003

Data Index: 1476442 (Python Code)

Max Activating Token Index: 599

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1064440 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1336. Min Act: -0.0003

Data Index: 1451478 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1382. Min Act: -0.0003

Data Index: 161639 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1366. Min Act: -0.0003

Data Index: 1541132 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1321. Min Act: -0.0003

Data Index: 1653323 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1320. Min Act: -0.0003

Data Index: 1423398 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1357. Min Act: -0.0003

Data Index: 1607168 (Python Code)

Max Activating Token Index: 211

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1357. Min Act: -0.0003

Data Index: 1518194 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1317. Min Act: -0.0003

Data Index: 1626730 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1564594 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1333. Min Act: -0.0003

Data Index: 1597181 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1348. Min Act: -0.0003

Data Index: 1486977 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1351. Min Act: -0.0003

Data Index: 1533599 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1197. Min Act: -0.0003

Data Index: 1578312 (Python Code)

Max Activating Token Index: 834