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

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

Neuron 5359 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3368. Min Range: -4.3368

Max Act: 4.3368. Min Act: -0.0000

Data Index: 85480 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 4.3368. Min Range: -4.3368

Max Act: 4.0035. Min Act: -0.0000

Data Index: 738300 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.8184. Min Act: -0.0000

Data Index: 118314 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.9017. Min Act: -0.0000

Data Index: 635892 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.6882. Min Act: -0.0000

Data Index: 9644 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.6648. Min Act: -0.0000

Data Index: 793060 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.4851. Min Act: -0.0000

Data Index: 936140 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.8264. Min Act: -0.0000

Data Index: 427825 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.4348. Min Act: -0.0000

Data Index: 415363 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.7590. Min Act: -0.0000

Data Index: 317996 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.5290. Min Act: -0.0000

Data Index: 611848 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.4763. Min Act: -0.0000

Data Index: 571527 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.4453. Min Act: -0.0000

Data Index: 418477 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.7256. Min Act: -0.0000

Data Index: 131104 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.3829. Min Act: -0.0000

Data Index: 191820 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.3856. Min Act: -0.0000

Data Index: 214450 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.3817. Min Act: -0.0000

Data Index: 1092742 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.2051. Min Act: -0.0000

Data Index: 891305 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.1603. Min Act: -0.0000

Data Index: 973014 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 4.3368. Min Range: -4.3368

Max Act: 3.4896. Min Act: -0.0000

Data Index: 81830 (C4 (Web Text))

Max Activating Token Index: 641