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

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

Neuron 3421 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: 0.6384. Min Range: -0.6384

Max Act: 0.6384. Min Act: -0.0000

Data Index: 276266 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.6195. Min Act: -0.0000

Data Index: 226955 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5435. Min Act: -0.0000

Data Index: 205430 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5016. Min Act: -0.0000

Data Index: 188196 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4994. Min Act: -0.0000

Data Index: 851608 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1032781 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4838. Min Act: -0.0000

Data Index: 7059 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4741. Min Act: -0.0000

Data Index: 249711 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4904. Min Act: -0.0000

Data Index: 860953 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1057572 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4561. Min Act: -0.0000

Data Index: 990575 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4763. Min Act: -0.0000

Data Index: 318012 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1098095 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4882. Min Act: -0.0000

Data Index: 326137 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4567. Min Act: -0.0000

Data Index: 502813 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4328. Min Act: -0.0000

Data Index: 777373 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4825. Min Act: -0.0000

Data Index: 122871 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.3825. Min Act: -0.0000

Data Index: 735308 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4246. Min Act: -0.0000

Data Index: 915407 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1335904 (C4 (Web Text))

Max Activating Token Index: 752