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

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

Neuron 2975 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1451039 (Python Code)

Max Activating Token Index: 764

Text #1

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1603332 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1498048 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1612568 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1504025 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1591444 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1440527 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1571478 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1616236 (Python Code)

Max Activating Token Index: 415

Text #9

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1617777 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1412115 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1537053 (Python Code)

Max Activating Token Index: 391

Text #12

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1587378 (Python Code)

Max Activating Token Index: 832

Text #13

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1473376 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1504199 (Python Code)

Max Activating Token Index: 565

Text #15

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1655631 (Python Code)

Max Activating Token Index: 710

Text #16

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1483813 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1560134 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1471546 (Python Code)

Max Activating Token Index: 317

Text #19

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1502077 (Python Code)

Max Activating Token Index: 364