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

Dataset: The Pile

Neuron 1746 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.9109. Min Act: -0.0000

Data Index: 314623 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.4830. Min Act: -0.0000

Data Index: 1907809 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.0834. Min Act: -0.0000

Data Index: 1822091 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.2566. Min Act: -0.0000

Data Index: 996280 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.9305. Min Act: -0.0000

Data Index: 607228 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.9128. Min Act: -0.0000

Data Index: 1324976 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.9087. Min Act: -0.0000

Data Index: 55326 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.9368. Min Act: -0.0000

Data Index: 841731 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.7563. Min Act: -0.0000

Data Index: 750514 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.8430. Min Act: -0.0000

Data Index: 1578531 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.9577. Min Act: -0.0000

Data Index: 238047 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.9216. Min Act: -0.0000

Data Index: 676260 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.0767. Min Act: -0.0000

Data Index: 738887 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.7967. Min Act: -0.0000

Data Index: 1908275 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.6481. Min Act: -0.0000

Data Index: 904443 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.7475. Min Act: -0.0000

Data Index: 995343 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.8717. Min Act: -0.0000

Data Index: 1560410 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1061894 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.7906. Min Act: -0.0000

Data Index: 1842942 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 3.9109. Min Range: -3.9109

Max Act: 2.6878. Min Act: -0.0000

Data Index: 1863515 (The Pile)

Max Activating Token Index: 539