Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3283 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1555718 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1410504 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.2171. Min Act: -0.0001

Data Index: 1637750 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1653290 (Python Code)

Max Activating Token Index: 268

Text #4

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1514817 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1593. Min Act: -0.0001

Data Index: 114501 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1495. Min Act: -0.0001

Data Index: 829041 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1492051 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1209808 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1444818 (Python Code)

Max Activating Token Index: 256

Text #10

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1539. Min Act: -0.0001

Data Index: 623842 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1601505 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1534. Min Act: -0.0001

Data Index: 513110 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1612066 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1453141 (Python Code)

Max Activating Token Index: 668

Text #15

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1508. Min Act: -0.0001

Data Index: 1596717 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1608824 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1490. Min Act: -0.0001

Data Index: 817406 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1601897 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1508951 (Python Code)

Max Activating Token Index: 470