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

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

Neuron 2246 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: 0.1699. Min Range: -0.1699

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1499384 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1613358 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1566185 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1423937 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1586. Min Act: -0.0002

Data Index: 1401229 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1468271 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1445627 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1515. Min Act: -0.0002

Data Index: 1439601 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1642880 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1595282 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1515004 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1522268 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1412793 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1404664 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1452250 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1543382 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1515473 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1438099 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1388344 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1361640 (Python Code)

Max Activating Token Index: 10