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

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

Neuron 1807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7870. Min Act: -0.0000

Data Index: 811308 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1146659 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5871. Min Act: -0.0000

Data Index: 961548 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5700. Min Act: -0.0000

Data Index: 42184 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6084. Min Act: -0.0000

Data Index: 620491 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1268376 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5640. Min Act: -0.0000

Data Index: 966011 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5718. Min Act: -0.0000

Data Index: 361936 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6692. Min Act: -0.0000

Data Index: 848689 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5388. Min Act: -0.0000

Data Index: 560970 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5822. Min Act: -0.0000

Data Index: 611110 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5153. Min Act: -0.0000

Data Index: 899367 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5277. Min Act: -0.0000

Data Index: 462315 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1213576 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.4341. Min Act: -0.0000

Data Index: 561007 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.4074. Min Act: -0.0000

Data Index: 325081 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1151625 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.3914. Min Act: -0.0000

Data Index: 697646 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.4256. Min Act: -0.0000

Data Index: 477571 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.3818. Min Act: -0.0000

Data Index: 731441 (C4 (Web Text))

Max Activating Token Index: 738