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

Dataset: The Pile

Neuron 570 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: 0.2144. Min Range: -0.2144

Max Act: 0.2144. Min Act: -0.0000

Data Index: 638121 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1885. Min Act: -0.0000

Data Index: 534200 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1157722 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1135616 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1708. Min Act: -0.0000

Data Index: 756039 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1898098 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1638349 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1408. Min Act: -0.0000

Data Index: 858291 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1420. Min Act: -0.0000

Data Index: 701848 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1561. Min Act: -0.0000

Data Index: 4328 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1228. Min Act: -0.0000

Data Index: 804034 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1329. Min Act: -0.0000

Data Index: 969216 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1524. Min Act: -0.0000

Data Index: 948996 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1476. Min Act: -0.0000

Data Index: 640732 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1469. Min Act: -0.0000

Data Index: 828023 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1851353 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1462. Min Act: -0.0000

Data Index: 253480 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1386407 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1451. Min Act: -0.0000

Data Index: 834993 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1818930 (The Pile)

Max Activating Token Index: 436