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

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

Neuron 1859 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: 0.8287. Min Range: -0.8287

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1100406 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7840. Min Act: -0.0001

Data Index: 794545 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7720. Min Act: -0.0001

Data Index: 370331 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8105. Min Act: -0.0001

Data Index: 799287 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6728. Min Act: -0.0001

Data Index: 331365 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7258. Min Act: -0.0001

Data Index: 711645 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6863. Min Act: -0.0001

Data Index: 695022 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7068. Min Act: -0.0001

Data Index: 1146962 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1035970 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7673. Min Act: -0.0001

Data Index: 193852 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7014. Min Act: -0.0001

Data Index: 60798 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7220. Min Act: -0.0001

Data Index: 1129351 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6823. Min Act: -0.0001

Data Index: 710383 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7045. Min Act: -0.0001

Data Index: 888697 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6589. Min Act: -0.0001

Data Index: 50954 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6774. Min Act: -0.0001

Data Index: 328447 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6529. Min Act: -0.0001

Data Index: 676203 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6438. Min Act: -0.0001

Data Index: 984609 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6999. Min Act: -0.0001

Data Index: 955637 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6507. Min Act: -0.0001

Data Index: 684074 (C4 (Web Text))

Max Activating Token Index: 55