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

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

Neuron 3807 in Layer 1

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: 0.1763. Min Range: -0.1763

Max Act: 0.1763. Min Act: -0.0002

Data Index: 1648359 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1690. Min Act: -0.0002

Data Index: 1510294 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1598. Min Act: -0.0002

Data Index: 1617670 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1591. Min Act: -0.0002

Data Index: 1457499 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1637850 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1518. Min Act: -0.0002

Data Index: 1451308 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1506. Min Act: -0.0002

Data Index: 1619802 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1495. Min Act: -0.0002

Data Index: 1601707 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1435632 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1412401 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1467. Min Act: -0.0002

Data Index: 1380987 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1480774 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1457. Min Act: -0.0002

Data Index: 1371172 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1437310 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1429. Min Act: -0.0002

Data Index: 1492849 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1448. Min Act: -0.0002

Data Index: 1443998 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1614530 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1401. Min Act: -0.0002

Data Index: 1426976 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1575999 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1610449 (Python Code)

Max Activating Token Index: 440