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

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

Neuron 3551 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0583. Min Act: -0.0002

Data Index: 34127 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0582. Min Act: -0.0002

Data Index: 792925 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0572. Min Act: -0.0002

Data Index: 862515 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1358875 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0520. Min Act: -0.0002

Data Index: 221183 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0493. Min Act: -0.0002

Data Index: 311751 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1092058 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1243752 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0443. Min Act: -0.0002

Data Index: 167883 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0494. Min Act: -0.0002

Data Index: 987242 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0460. Min Act: -0.0002

Data Index: 300471 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0411. Min Act: -0.0002

Data Index: 759569 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0425. Min Act: -0.0002

Data Index: 216538 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1115037 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0432. Min Act: -0.0002

Data Index: 359668 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0389. Min Act: -0.0002

Data Index: 322603 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0438. Min Act: -0.0002

Data Index: 101750 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0395. Min Act: -0.0002

Data Index: 112642 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1051770 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1095492 (C4 (Web Text))

Max Activating Token Index: 875