Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 12 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1509750 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1723. Min Act: -0.0002

Data Index: 1475163 (Python Code)

Max Activating Token Index: 855

Text #2

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1645. Min Act: -0.0002

Data Index: 1505478 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1659. Min Act: -0.0002

Data Index: 1578660 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1653. Min Act: -0.0002

Data Index: 143440 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1557. Min Act: -0.0002

Data Index: 1516201 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1574. Min Act: -0.0002

Data Index: 1523476 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1553. Min Act: -0.0002

Data Index: 924595 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1535. Min Act: -0.0002

Data Index: 1587427 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1377240 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1495. Min Act: -0.0002

Data Index: 1101144 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1429. Min Act: -0.0002

Data Index: 1491258 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1605. Min Act: -0.0002

Data Index: 781075 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1538. Min Act: -0.0002

Data Index: 1550051 (Python Code)

Max Activating Token Index: 674

Text #14

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1389594 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1352627 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1479009 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1479. Min Act: -0.0002

Data Index: 1362964 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1445137 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1450. Min Act: -0.0002

Data Index: 1415407 (Python Code)

Max Activating Token Index: 429