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

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

Neuron 2625 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: 1.2078. Min Range: -1.2078

Max Act: 1.2078. Min Act: -0.0001

Data Index: 987373 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.1496. Min Act: -0.0001

Data Index: 907056 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.1785. Min Act: -0.0001

Data Index: 124549 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0608. Min Act: -0.0001

Data Index: 275234 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0551. Min Act: -0.0001

Data Index: 1277565 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9752. Min Act: -0.0001

Data Index: 972982 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0553. Min Act: -0.0001

Data Index: 261297 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9795. Min Act: -0.0001

Data Index: 1097588 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9530. Min Act: -0.0001

Data Index: 18003 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9833. Min Act: -0.0001

Data Index: 990879 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8642. Min Act: -0.0001

Data Index: 893011 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8876. Min Act: -0.0001

Data Index: 108755 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8693. Min Act: -0.0001

Data Index: 44929 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8565. Min Act: -0.0001

Data Index: 1352371 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8522. Min Act: -0.0001

Data Index: 112519 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8407. Min Act: -0.0001

Data Index: 135478 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8465. Min Act: -0.0001

Data Index: 574073 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8390. Min Act: -0.0001

Data Index: 737200 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8905. Min Act: -0.0001

Data Index: 1288142 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8268. Min Act: -0.0001

Data Index: 632591 (C4 (Web Text))

Max Activating Token Index: 725