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

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

Neuron 2324 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: 0.5694. Min Range: -0.5694

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1333010 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.5465. Min Act: -0.0000

Data Index: 830884 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4896. Min Act: -0.0000

Data Index: 732611 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4556. Min Act: -0.0000

Data Index: 594304 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4546. Min Act: 0.0001

Data Index: 444244 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4327. Min Act: -0.0000

Data Index: 158932 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4173. Min Act: 0.0001

Data Index: 265925 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4030. Min Act: -0.0000

Data Index: 899217 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4201. Min Act: 0.0000

Data Index: 481323 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.4174. Min Act: -0.0000

Data Index: 686622 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3834. Min Act: 0.0000

Data Index: 1296262 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3840. Min Act: -0.0000

Data Index: 687383 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3797. Min Act: -0.0000

Data Index: 746465 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1146981 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1241539 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3574. Min Act: -0.0000

Data Index: 598519 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3236. Min Act: 0.0001

Data Index: 396256 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3562. Min Act: 0.0001

Data Index: 656504 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1212757 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.5694. Min Range: -0.5694

Max Act: 0.3464. Min Act: 0.0000

Data Index: 73643 (C4 (Web Text))

Max Activating Token Index: 997