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

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

Neuron 3635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.6367. Min Act: -0.0000

Data Index: 422591 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1025478 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1171181 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5839. Min Act: -0.0000

Data Index: 716767 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1333816 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5396. Min Act: -0.0000

Data Index: 885945 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5510. Min Act: -0.0000

Data Index: 186161 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4820. Min Act: -0.0000

Data Index: 415476 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1277324 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1218642 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1200640 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1306970 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1043666 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1144329 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4770. Min Act: -0.0000

Data Index: 417384 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1193851 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1032177 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4809. Min Act: -0.0000

Data Index: 856563 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4566. Min Act: -0.0000

Data Index: 798430 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4805. Min Act: -0.0000

Data Index: 110545 (C4 (Web Text))

Max Activating Token Index: 912