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

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

Neuron 2907 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: 0.1803. Min Range: -0.1803

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1483424 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1497342 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1370846 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1495075 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1588666 (Python Code)

Max Activating Token Index: 601

Text #5

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1386569 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1422132 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1439487 (Python Code)

Max Activating Token Index: 168

Text #8

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1555769 (Python Code)

Max Activating Token Index: 755

Text #9

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1434659 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1449. Min Act: -0.0002

Data Index: 1379630 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1460920 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1500420 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1441. Min Act: -0.0002

Data Index: 1481458 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1645622 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1495814 (Python Code)

Max Activating Token Index: 396

Text #16

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1450179 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1458360 (Python Code)

Max Activating Token Index: 624

Text #18

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1608492 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1637950 (Python Code)

Max Activating Token Index: 32