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

Dataset: The Pile

Neuron 3315 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: 0.2368. Min Range: -0.2368

Max Act: 0.2368. Min Act: -0.0000

Data Index: 639512 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2112. Min Act: -0.0000

Data Index: 375417 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1619. Min Act: -0.0000

Data Index: 379539 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1293129 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1739. Min Act: -0.0000

Data Index: 471457 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1050253 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1499. Min Act: -0.0000

Data Index: 71677 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1493. Min Act: -0.0000

Data Index: 293310 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1057446 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1598. Min Act: -0.0000

Data Index: 756085 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1396. Min Act: -0.0000

Data Index: 227687 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1128791 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1628712 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1338. Min Act: -0.0000

Data Index: 780631 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1454619 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1808341 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1363. Min Act: -0.0000

Data Index: 514059 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1474. Min Act: -0.0000

Data Index: 868800 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1082074 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1224. Min Act: -0.0000

Data Index: 142889 (The Pile)

Max Activating Token Index: 734