Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0001

Data Index: 448152 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0780. Min Act: -0.0001

Data Index: 878060 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0737. Min Act: -0.0001

Data Index: 6026 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0734. Min Act: -0.0001

Data Index: 269926 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0704. Min Act: -0.0001

Data Index: 603630 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0711. Min Act: -0.0001

Data Index: 801341 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1060346 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1288866 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1115439 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1060418 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0701. Min Act: -0.0001

Data Index: 326232 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0676. Min Act: -0.0001

Data Index: 408888 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0704. Min Act: -0.0001

Data Index: 170986 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0676. Min Act: -0.0001

Data Index: 258904 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1233590 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0692. Min Act: -0.0002

Data Index: 153770 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0709. Min Act: -0.0001

Data Index: 392414 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1292137 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0638. Min Act: -0.0002

Data Index: 661596 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1117085 (C4 (Web Text))

Max Activating Token Index: 214