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

Dataset: The Pile

Neuron 3677 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: 0.2518. Min Range: -0.2518

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1040872 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1051188 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1355015 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1866. Min Act: -0.0000

Data Index: 509756 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1621. Min Act: -0.0000

Data Index: 444996 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1322462 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1650. Min Act: -0.0000

Data Index: 887746 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1269105 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1411. Min Act: -0.0000

Data Index: 518237 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1706198 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1558. Min Act: -0.0000

Data Index: 299067 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1814982 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1394. Min Act: -0.0000

Data Index: 79016 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1457. Min Act: -0.0000

Data Index: 933491 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1381. Min Act: -0.0000

Data Index: 356143 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1382. Min Act: -0.0000

Data Index: 12529 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1196891 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1712293 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1352. Min Act: -0.0000

Data Index: 358712 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1094790 (The Pile)

Max Activating Token Index: 630