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

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

Neuron 4664 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1224349 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0002

Data Index: 730742 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1317908 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1342413 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0655. Min Act: -0.0002

Data Index: 853045 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0616. Min Act: -0.0002

Data Index: 335649 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0605. Min Act: -0.0002

Data Index: 732479 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0608. Min Act: -0.0002

Data Index: 967555 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1314141 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0590. Min Act: -0.0002

Data Index: 282435 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0589. Min Act: -0.0002

Data Index: 994277 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0582. Min Act: -0.0002

Data Index: 630471 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0518. Min Act: -0.0002

Data Index: 475005 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0537. Min Act: -0.0002

Data Index: 974190 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1318849 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1325974 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0560. Min Act: -0.0002

Data Index: 312663 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0562. Min Act: -0.0002

Data Index: 703013 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1042602 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0525. Min Act: -0.0002

Data Index: 426478 (C4 (Web Text))

Max Activating Token Index: 93