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

Dataset: The Pile

Neuron 4369 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: 0.3512. Min Range: -0.3512

Max Act: 0.3381. Min Act: -0.0000

Data Index: 844504 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3317. Min Act: -0.0000

Data Index: 24029 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3068. Min Act: -0.0000

Data Index: 528453 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1388017 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3206. Min Act: -0.0000

Data Index: 209015 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1187876 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3512. Min Act: -0.0000

Data Index: 671007 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1554127 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1734749 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2709. Min Act: -0.0000

Data Index: 625199 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2815. Min Act: -0.0000

Data Index: 574828 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1325038 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1513646 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2632. Min Act: -0.0000

Data Index: 229813 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2448. Min Act: -0.0000

Data Index: 731815 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1635824 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1840402 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3066. Min Act: -0.0000

Data Index: 332019 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2776. Min Act: -0.0000

Data Index: 971395 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2752. Min Act: -0.0000

Data Index: 957674 (The Pile)

Max Activating Token Index: 885