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

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

Neuron 4596 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.6436. Min Act: -0.0000

Data Index: 1656877 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.5955. Min Act: -0.0000

Data Index: 1555475 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2828. Min Act: -0.0001

Data Index: 1655472 (Python Code)

Max Activating Token Index: 972

Text #3

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1622394 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1571714 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.3151. Min Act: -0.0001

Data Index: 1439155 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1543947 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1362462 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1576418 (Python Code)

Max Activating Token Index: 943

Text #9

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1655477 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1433294 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2526. Min Act: -0.0001

Data Index: 1541582 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1401593 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1521068 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2510. Min Act: -0.0001

Data Index: 1603035 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1625101 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.0076. Min Act: -0.0001

Data Index: 1537786 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1392848 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1385800 (Python Code)

Max Activating Token Index: 652

Text #19

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1405046 (Python Code)

Max Activating Token Index: 240