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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 415 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0051. Min Range: -1.0051

Max Act: 1.0051. Min Act: -0.0001

Data Index: 515623 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8734. Min Act: -0.0001

Data Index: 461695 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8115. Min Act: -0.0001

Data Index: 459969 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8667. Min Act: -0.0001

Data Index: 626768 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8101. Min Act: -0.0001

Data Index: 195869 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8275. Min Act: -0.0001

Data Index: 822226 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8732. Min Act: -0.0001

Data Index: 255393 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8501. Min Act: -0.0001

Data Index: 27847 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8193. Min Act: -0.0001

Data Index: 315374 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7914. Min Act: -0.0001

Data Index: 170863 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8088. Min Act: -0.0001

Data Index: 739261 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7752. Min Act: -0.0001

Data Index: 171245 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7943. Min Act: -0.0001

Data Index: 14887 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7943. Min Act: -0.0001

Data Index: 600359 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.6927. Min Act: -0.0001

Data Index: 267765 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7348. Min Act: -0.0001

Data Index: 660525 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7774. Min Act: -0.0001

Data Index: 747343 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7088. Min Act: -0.0001

Data Index: 1213054 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.6994. Min Act: -0.0001

Data Index: 153066 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1229324 (C4 (Web Text))

Max Activating Token Index: 334