Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 574 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0005

Data Index: 645624 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0451. Min Act: -0.0005

Data Index: 808683 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0486. Min Act: -0.0005

Data Index: 226408 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0413. Min Act: -0.0005

Data Index: 432021 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0378. Min Act: -0.0005

Data Index: 263355 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0408. Min Act: -0.0005

Data Index: 1206122 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0408. Min Act: -0.0005

Data Index: 8964 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0405. Min Act: -0.0005

Data Index: 140450 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0430. Min Act: -0.0005

Data Index: 538102 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0419. Min Act: -0.0005

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0420. Min Act: -0.0005

Data Index: 205917 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0417. Min Act: -0.0005

Data Index: 1307276 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0404. Min Act: -0.0005

Data Index: 677376 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0416. Min Act: -0.0005

Data Index: 1347854 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0413. Min Act: -0.0005

Data Index: 868136 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0406. Min Act: -0.0005

Data Index: 207384 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0402. Min Act: -0.0005

Data Index: 776673 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0405. Min Act: -0.0005

Data Index: 1112723 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0380. Min Act: -0.0005

Data Index: 834279 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0400. Min Act: -0.0005

Data Index: 957627 (C4 (Web Text))

Max Activating Token Index: 512