Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.4506. Min Range: -7.4506

Max Act: 7.3669. Min Act: -0.0000

Data Index: 1100239 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.8561. Min Act: -0.0000

Data Index: 347463 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 7.4506. Min Range: -7.4506

Max Act: 7.4506. Min Act: -0.0000

Data Index: 146411 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.9606. Min Act: -0.0000

Data Index: 209723 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.8839. Min Act: -0.0000

Data Index: 1308593 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.6822. Min Act: -0.0000

Data Index: 330763 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.5034. Min Act: -0.0000

Data Index: 454427 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.3048. Min Act: -0.0000

Data Index: 276387 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.6411. Min Act: -0.0000

Data Index: 694091 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.6725. Min Act: -0.0000

Data Index: 728138 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.0597. Min Act: -0.0000

Data Index: 38392 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 7.4506. Min Range: -7.4506

Max Act: 5.9714. Min Act: -0.0000

Data Index: 1222598 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 7.4506. Min Range: -7.4506

Max Act: 5.9656. Min Act: -0.0000

Data Index: 168211 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.2549. Min Act: -0.0000

Data Index: 1075264 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.2220. Min Act: -0.0000

Data Index: 301430 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 7.4506. Min Range: -7.4506

Max Act: 5.9320. Min Act: -0.0000

Data Index: 588821 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.0853. Min Act: -0.0000

Data Index: 477910 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 7.4506. Min Range: -7.4506

Max Act: 5.8794. Min Act: -0.0000

Data Index: 516232 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 7.4506. Min Range: -7.4506

Max Act: 6.0810. Min Act: -0.0000

Data Index: 212244 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 7.4506. Min Range: -7.4506

Max Act: 5.9583. Min Act: -0.0000

Data Index: 1006032 (C4 (Web Text))

Max Activating Token Index: 478