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

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

Neuron 2118 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1588487 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1553468 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1554447 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1387992 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1487573 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1645198 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1462338 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1499940 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1386473 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1422611 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1414903 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1570941 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1403030 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1567948 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1573837 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1649126 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1545689 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1567502 (Python Code)

Max Activating Token Index: 380

Text #18

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1474284 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1624194 (Python Code)

Max Activating Token Index: 68