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

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

Neuron 4422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1556. Min Range: -3.1556

Max Act: 3.1556. Min Act: -0.0000

Data Index: 1190843 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.9890. Min Act: -0.0000

Data Index: 681338 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.8027. Min Act: -0.0000

Data Index: 869080 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.8870. Min Act: -0.0000

Data Index: 182289 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.8718. Min Act: -0.0000

Data Index: 1141890 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.8540. Min Act: -0.0000

Data Index: 670686 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.9809. Min Act: -0.0000

Data Index: 389842 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.9444. Min Act: -0.0000

Data Index: 94807 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.6572. Min Act: -0.0000

Data Index: 1062607 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.7948. Min Act: -0.0000

Data Index: 798739 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.5466. Min Act: -0.0000

Data Index: 499423 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.5414. Min Act: -0.0000

Data Index: 864147 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.5273. Min Act: -0.0000

Data Index: 145015 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.6546. Min Act: -0.0000

Data Index: 694546 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.6542. Min Act: -0.0000

Data Index: 441434 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.6519. Min Act: -0.0000

Data Index: 919676 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.7864. Min Act: -0.0000

Data Index: 1248015 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.8000. Min Act: -0.0000

Data Index: 983926 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.4675. Min Act: -0.0000

Data Index: 1332293 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 3.1556. Min Range: -3.1556

Max Act: 2.6029. Min Act: -0.0000

Data Index: 409891 (C4 (Web Text))

Max Activating Token Index: 190