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

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

Neuron 2310 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: 1.1833. Min Range: -1.1833

Max Act: 1.1833. Min Act: -0.0001

Data Index: 271641 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.0688. Min Act: -0.0001

Data Index: 1056985 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.1594. Min Act: -0.0001

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9634. Min Act: -0.0001

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9474. Min Act: -0.0001

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8640. Min Act: -0.0001

Data Index: 1387664 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9106. Min Act: -0.0001

Data Index: 565966 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9082. Min Act: -0.0001

Data Index: 288743 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9589. Min Act: -0.0001

Data Index: 921345 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9730. Min Act: -0.0001

Data Index: 283768 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.1420. Min Act: -0.0001

Data Index: 584902 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9239. Min Act: -0.0001

Data Index: 1153061 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9420. Min Act: -0.0001

Data Index: 754291 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1300353 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8783. Min Act: -0.0001

Data Index: 838117 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8465. Min Act: -0.0001

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8639. Min Act: -0.0001

Data Index: 1567257 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8650. Min Act: -0.0001

Data Index: 1567521 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8128. Min Act: -0.0001

Data Index: 396876 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8586. Min Act: -0.0001

Data Index: 1341908 (C4 (Web Text))

Max Activating Token Index: 466