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

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

Neuron 135 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.8718. Min Act: -0.0001

Data Index: 721009 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7616. Min Act: -0.0001

Data Index: 139460 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7438. Min Act: -0.0001

Data Index: 1096203 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7219. Min Act: -0.0001

Data Index: 366898 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7164. Min Act: -0.0001

Data Index: 800328 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6783. Min Act: -0.0001

Data Index: 440637 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6358. Min Act: -0.0001

Data Index: 1173752 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6723. Min Act: -0.0001

Data Index: 1107295 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6858. Min Act: -0.0001

Data Index: 724717 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1318415 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7241. Min Act: -0.0001

Data Index: 629192 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7351. Min Act: -0.0001

Data Index: 629594 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6799. Min Act: -0.0001

Data Index: 16214 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6923. Min Act: -0.0001

Data Index: 33797 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6788. Min Act: -0.0001

Data Index: 864245 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1311256 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1051698 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6623. Min Act: -0.0001

Data Index: 629200 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6306. Min Act: -0.0001

Data Index: 748159 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.5973. Min Act: -0.0001

Data Index: 68977 (C4 (Web Text))

Max Activating Token Index: 844