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

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

Neuron 137 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: 0.9974. Min Range: -0.9974

Max Act: 0.9974. Min Act: -0.0001

Data Index: 492039 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8998. Min Act: -0.0001

Data Index: 798324 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9056. Min Act: -0.0001

Data Index: 328587 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9242. Min Act: -0.0001

Data Index: 604775 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8739. Min Act: -0.0001

Data Index: 811406 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9229. Min Act: -0.0001

Data Index: 386042 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8315. Min Act: -0.0001

Data Index: 920188 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8529. Min Act: -0.0001

Data Index: 419859 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8003. Min Act: -0.0001

Data Index: 508192 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8406. Min Act: -0.0001

Data Index: 952673 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7956. Min Act: -0.0001

Data Index: 399592 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9012. Min Act: -0.0001

Data Index: 308284 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7849. Min Act: -0.0001

Data Index: 329109 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7771. Min Act: -0.0001

Data Index: 717259 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8017. Min Act: -0.0001

Data Index: 195203 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1220005 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8052. Min Act: -0.0001

Data Index: 130668 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7990. Min Act: -0.0001

Data Index: 730 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7552. Min Act: -0.0001

Data Index: 170180 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7274. Min Act: -0.0001

Data Index: 494390 (C4 (Web Text))

Max Activating Token Index: 936