Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3626 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1286853 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8804. Min Act: -0.0000

Data Index: 395653 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9548. Min Act: -0.0000

Data Index: 393511 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1086890 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9192. Min Act: -0.0000

Data Index: 70343 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1417681 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1632795 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1190875 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1667406 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1477357 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1235938 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7813. Min Act: -0.0000

Data Index: 685625 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1392295 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7378. Min Act: -0.0000

Data Index: 584437 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1539334 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1774853 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7131. Min Act: -0.0000

Data Index: 882211 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6769. Min Act: -0.0000

Data Index: 690251 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1150433 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7050. Min Act: -0.0000

Data Index: 465398 (The Pile)

Max Activating Token Index: 25