Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3080 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1644. Min Act: -0.0001

Data Index: 3972 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1241517 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1686. Min Act: -0.0001

Data Index: 838576 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1044756 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1647. Min Act: -0.0001

Data Index: 392595 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1537. Min Act: -0.0001

Data Index: 400780 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1296998 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1534. Min Act: -0.0001

Data Index: 982110 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1561. Min Act: -0.0001

Data Index: 970811 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1220142 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1493. Min Act: -0.0001

Data Index: 736586 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1476707 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1502. Min Act: -0.0001

Data Index: 672289 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1009319 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1254445 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1374. Min Act: -0.0001

Data Index: 371645 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1433. Min Act: -0.0001

Data Index: 220406 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1475. Min Act: -0.0001

Data Index: 65946 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1116628 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1310. Min Act: -0.0001

Data Index: 221925 (C4 (Web Text))

Max Activating Token Index: 874