Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5417 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1664. Min Range: -4.1664

Max Act: 4.1664. Min Act: -0.0000

Data Index: 599120 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.8290. Min Act: -0.0000

Data Index: 251171 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.8031. Min Act: -0.0000

Data Index: 735131 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.3220. Min Act: -0.0000

Data Index: 701584 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.6569. Min Act: -0.0000

Data Index: 303034 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.3250. Min Act: -0.0000

Data Index: 127945 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2920. Min Act: -0.0000

Data Index: 774033 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.4174. Min Act: -0.0000

Data Index: 331199 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2798. Min Act: -0.0000

Data Index: 767713 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2823. Min Act: -0.0000

Data Index: 829384 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2112. Min Act: -0.0000

Data Index: 426270 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2033. Min Act: -0.0000

Data Index: 1062975 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2086. Min Act: -0.0000

Data Index: 1315722 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1397. Min Act: -0.0000

Data Index: 459181 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.9414. Min Act: -0.0000

Data Index: 1158930 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.0630. Min Act: -0.0000

Data Index: 1244341 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.9957. Min Act: -0.0000

Data Index: 720609 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.9767. Min Act: -0.0000

Data Index: 701072 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.9481. Min Act: -0.0000

Data Index: 1022437 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1113. Min Act: -0.0000

Data Index: 1292248 (C4 (Web Text))

Max Activating Token Index: 350