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

Dataset: The Pile

Neuron 2371 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: 0.3010. Min Range: -0.3010

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1596940 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2442. Min Act: -0.0000

Data Index: 993175 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2457. Min Act: -0.0000

Data Index: 998222 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2027. Min Act: -0.0000

Data Index: 830157 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2194. Min Act: -0.0000

Data Index: 900647 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2277. Min Act: -0.0000

Data Index: 613940 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1302910 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1837. Min Act: -0.0000

Data Index: 771366 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1398914 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1896. Min Act: -0.0000

Data Index: 358938 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1801. Min Act: -0.0000

Data Index: 524823 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1303541 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1800. Min Act: -0.0000

Data Index: 882100 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1964187 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1660. Min Act: -0.0000

Data Index: 755763 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1731310 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1388026 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1344533 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1770500 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1171746 (The Pile)

Max Activating Token Index: 976