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

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

Neuron 4003 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: 0.5599. Min Range: -0.5599

Max Act: 0.5599. Min Act: 0.0001

Data Index: 204448 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.5447. Min Act: -0.0000

Data Index: 978736 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.5055. Min Act: -0.0000

Data Index: 274289 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1281810 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4819. Min Act: -0.0000

Data Index: 737495 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4354. Min Act: -0.0000

Data Index: 575217 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1111322 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1233362 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3939. Min Act: -0.0000

Data Index: 732839 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4121. Min Act: -0.0000

Data Index: 649934 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4084. Min Act: -0.0000

Data Index: 645248 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4044. Min Act: -0.0000

Data Index: 549961 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4022. Min Act: -0.0000

Data Index: 775945 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4003. Min Act: -0.0000

Data Index: 869187 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3696. Min Act: -0.0000

Data Index: 552173 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3766. Min Act: -0.0000

Data Index: 718771 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3756. Min Act: 0.0000

Data Index: 1347167 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3590. Min Act: -0.0000

Data Index: 364612 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3713. Min Act: -0.0000

Data Index: 140717 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3583. Min Act: -0.0000

Data Index: 872624 (C4 (Web Text))

Max Activating Token Index: 1016