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

Dataset: The Pile

Neuron 3751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1594. Min Act: -0.0000

Data Index: 708135 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1675. Min Act: -0.0000

Data Index: 248412 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1798. Min Act: -0.0000

Data Index: 623780 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1491. Min Act: -0.0000

Data Index: 161941 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1211748 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1608. Min Act: -0.0000

Data Index: 961479 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1642. Min Act: -0.0000

Data Index: 890931 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1425739 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1489. Min Act: -0.0000

Data Index: 241873 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1462. Min Act: -0.0000

Data Index: 261231 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1419443 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1476611 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1588. Min Act: -0.0000

Data Index: 895059 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1183023 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1054002 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1785956 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1359. Min Act: -0.0000

Data Index: 438857 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1329979 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1403. Min Act: -0.0000

Data Index: 370404 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1403. Min Act: -0.0000

Data Index: 210347 (The Pile)

Max Activating Token Index: 332