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

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

Neuron 4602 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: 1.3111. Min Range: -1.3111

Max Act: 1.3111. Min Act: -0.0001

Data Index: 828315 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8777. Min Act: -0.0001

Data Index: 1241326 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9242. Min Act: -0.0001

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9456. Min Act: -0.0001

Data Index: 479526 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9175. Min Act: -0.0001

Data Index: 293169 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8875. Min Act: -0.0001

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8445. Min Act: -0.0001

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9004. Min Act: -0.0001

Data Index: 253896 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8849. Min Act: -0.0001

Data Index: 290129 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9331. Min Act: -0.0001

Data Index: 968494 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8715. Min Act: -0.0001

Data Index: 1072705 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7667. Min Act: -0.0001

Data Index: 411221 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1209307 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9138. Min Act: -0.0001

Data Index: 1300428 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7111. Min Act: -0.0001

Data Index: 669071 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1137428 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7400. Min Act: -0.0001

Data Index: 206629 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1096081 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7520. Min Act: -0.0001

Data Index: 324723 (C4 (Web Text))

Max Activating Token Index: 208