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

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

Neuron 2213 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9267. Min Act: -0.0001

Data Index: 827599 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8885. Min Act: -0.0001

Data Index: 496209 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8773. Min Act: -0.0001

Data Index: 473477 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8634. Min Act: -0.0001

Data Index: 593341 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8733. Min Act: -0.0001

Data Index: 488232 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8429. Min Act: -0.0001

Data Index: 425588 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8488. Min Act: -0.0001

Data Index: 734660 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1337665 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7904. Min Act: -0.0001

Data Index: 461961 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7849. Min Act: -0.0001

Data Index: 982761 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7860. Min Act: -0.0001

Data Index: 795903 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1197347 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7269. Min Act: -0.0001

Data Index: 1288894 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7963. Min Act: -0.0001

Data Index: 810989 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7062. Min Act: -0.0001

Data Index: 129737 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7491. Min Act: -0.0001

Data Index: 985595 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7658. Min Act: -0.0001

Data Index: 628224 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1095620 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7565. Min Act: -0.0001

Data Index: 195573 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7262. Min Act: -0.0001

Data Index: 183131 (C4 (Web Text))

Max Activating Token Index: 531