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

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

Neuron 3902 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: 0.6733. Min Range: -0.6733

Max Act: 0.6733. Min Act: -0.0001

Data Index: 93399 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6082. Min Act: -0.0001

Data Index: 301370 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6167. Min Act: -0.0001

Data Index: 1068214 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6625. Min Act: -0.0001

Data Index: 685846 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6283. Min Act: -0.0001

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5767. Min Act: -0.0001

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5437. Min Act: -0.0001

Data Index: 1258642 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5555. Min Act: -0.0001

Data Index: 524107 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5703. Min Act: -0.0001

Data Index: 535923 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1081517 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5490. Min Act: -0.0001

Data Index: 522012 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5294. Min Act: -0.0001

Data Index: 477046 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1312120 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1250155 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5223. Min Act: -0.0001

Data Index: 999037 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5229. Min Act: -0.0001

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1336994 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5316. Min Act: -0.0001

Data Index: 428482 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5327. Min Act: -0.0001

Data Index: 249466 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5105. Min Act: -0.0001

Data Index: 601128 (C4 (Web Text))

Max Activating Token Index: 223