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

Dataset: The Pile

Neuron 2167 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: 0.3816. Min Range: -0.3816

Max Act: 0.3816. Min Act: -0.0000

Data Index: 49320 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1003669 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.3071. Min Act: -0.0000

Data Index: 79168 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2974. Min Act: -0.0000

Data Index: 986203 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2709. Min Act: -0.0000

Data Index: 590534 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1893547 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1007355 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1749180 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1033377 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1628075 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2393. Min Act: -0.0000

Data Index: 652396 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2686. Min Act: -0.0000

Data Index: 67999 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1106317 (The Pile)

Max Activating Token Index: 921

Text #13

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2270. Min Act: -0.0000

Data Index: 100238 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1472047 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1471237 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1591057 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2028. Min Act: -0.0000

Data Index: 417810 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2115. Min Act: -0.0000

Data Index: 474255 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1833074 (The Pile)

Max Activating Token Index: 744