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

Dataset: The Pile

Neuron 4105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1462482 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1016079 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1022410 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1560240 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1225302 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1623595 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1897311 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1601. Min Act: -0.0000

Data Index: 566650 (The Pile)

Max Activating Token Index: 165

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1595243 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1252041 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1505. Min Act: -0.0000

Data Index: 573537 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1535. Min Act: -0.0000

Data Index: 508389 (The Pile)

Max Activating Token Index: 686

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1498. Min Act: -0.0000

Data Index: 993680 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1479. Min Act: -0.0000

Data Index: 672420 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1527. Min Act: -0.0000

Data Index: 374164 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1352. Min Act: -0.0000

Data Index: 941206 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1537503 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1095601 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1860700 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1749657 (The Pile)

Max Activating Token Index: 148