Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 39 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1493. Min Act: -0.0001

Data Index: 1430485 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0667. Min Act: -0.0001

Data Index: 1419713 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1075. Min Act: -0.0001

Data Index: 1572343 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0302. Min Act: -0.0001

Data Index: 1480435 (Python Code)

Max Activating Token Index: 318

Text #4

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1440941 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9778. Min Act: -0.0001

Data Index: 1467827 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0365. Min Act: -0.0001

Data Index: 1613521 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1498815 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0594. Min Act: -0.0001

Data Index: 1544993 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1412203 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9523. Min Act: -0.0001

Data Index: 1460777 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9676. Min Act: -0.0001

Data Index: 1434472 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9719. Min Act: -0.0001

Data Index: 1656048 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1017. Min Act: -0.0001

Data Index: 1507218 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1434985 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0863. Min Act: -0.0001

Data Index: 1503330 (Python Code)

Max Activating Token Index: 755

Text #16

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1521616 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1404104 (Python Code)

Max Activating Token Index: 499

Text #18

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9024. Min Act: -0.0001

Data Index: 1446386 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0591. Min Act: -0.0001

Data Index: 1376489 (Python Code)

Max Activating Token Index: 811