Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2239 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1893. Min Act: 0.0000

Data Index: 1847816 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1998. Min Act: -0.0000

Data Index: 725593 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1709. Min Act: -0.0001

Data Index: 212631 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1261309 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1398211 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1622. Min Act: -0.0000

Data Index: 89660 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1558. Min Act: -0.0000

Data Index: 756766 (The Pile)

Max Activating Token Index: 845

Text #7

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1490. Min Act: -0.0000

Data Index: 215405 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1580041 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1554. Min Act: -0.0000

Data Index: 761379 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1374. Min Act: -0.0000

Data Index: 227760 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1426. Min Act: -0.0000

Data Index: 382063 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1649167 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1688078 (The Pile)

Max Activating Token Index: 474

Text #14

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1742988 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1412. Min Act: -0.0000

Data Index: 878783 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1459. Min Act: -0.0000

Data Index: 675969 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1432. Min Act: -0.0000

Data Index: 164975 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1332. Min Act: -0.0001

Data Index: 535298 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1367. Min Act: -0.0000

Data Index: 365214 (The Pile)

Max Activating Token Index: 323