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

Dataset: The Pile

Neuron 1750 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1858682 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2033. Min Act: -0.0000

Data Index: 526126 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1771. Min Act: -0.0000

Data Index: 966480 (The Pile)

Max Activating Token Index: 266

Text #3

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1797. Min Act: -0.0000

Data Index: 84223 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1476. Min Act: -0.0000

Data Index: 638678 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1563. Min Act: -0.0000

Data Index: 495340 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1525. Min Act: -0.0000

Data Index: 356049 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1654707 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1815932 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1405. Min Act: -0.0000

Data Index: 108005 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1433. Min Act: -0.0000

Data Index: 17771 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1533. Min Act: -0.0000

Data Index: 756375 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1446. Min Act: -0.0000

Data Index: 603498 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1227. Min Act: -0.0000

Data Index: 755802 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1279. Min Act: -0.0001

Data Index: 734910 (The Pile)

Max Activating Token Index: 144

Text #15

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1353. Min Act: -0.0000

Data Index: 203700 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1185. Min Act: -0.0000

Data Index: 884307 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1601631 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1791728 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1537706 (The Pile)

Max Activating Token Index: 498