Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1968 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4703. Min Act: -0.0001

Data Index: 134082 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3222. Min Act: 0.0001

Data Index: 849345 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1046016 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3374. Min Act: 0.0001

Data Index: 1111646 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3148. Min Act: -0.0000

Data Index: 673153 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3026. Min Act: -0.0001

Data Index: 378817 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3034. Min Act: -0.0001

Data Index: 735654 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2672. Min Act: 0.0002

Data Index: 142010 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2865. Min Act: 0.0002

Data Index: 881633 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2811. Min Act: -0.0001

Data Index: 95658 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2792. Min Act: 0.0005

Data Index: 168723 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1303004 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2724. Min Act: 0.0000

Data Index: 637148 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2627. Min Act: 0.0004

Data Index: 781004 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2570. Min Act: -0.0001

Data Index: 582533 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2621. Min Act: 0.0001

Data Index: 763611 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1139945 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2510. Min Act: 0.0002

Data Index: 315258 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2516. Min Act: 0.0000

Data Index: 630464 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2495. Min Act: 0.0002

Data Index: 1246983 (C4 (Web Text))

Max Activating Token Index: 342