Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 794 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0006

Data Index: 222266 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0455. Min Act: -0.0006

Data Index: 652628 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0453. Min Act: -0.0006

Data Index: 1192727 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0450. Min Act: -0.0006

Data Index: 690404 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0406. Min Act: -0.0006

Data Index: 133446 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1022788 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0409. Min Act: -0.0006

Data Index: 467500 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1355394 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0425. Min Act: -0.0006

Data Index: 1137202 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0415. Min Act: -0.0006

Data Index: 1343335 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0388. Min Act: -0.0006

Data Index: 1126047 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0414. Min Act: -0.0006

Data Index: 653492 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0403. Min Act: -0.0006

Data Index: 5049 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0411. Min Act: -0.0006

Data Index: 208272 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0401. Min Act: -0.0006

Data Index: 386534 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0411. Min Act: -0.0006

Data Index: 884575 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0390. Min Act: -0.0006

Data Index: 236827 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0415. Min Act: -0.0005

Data Index: 103774 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1077818 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0400. Min Act: -0.0006

Data Index: 776564 (C4 (Web Text))

Max Activating Token Index: 286