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

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

Neuron 1752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0000

Data Index: 588785 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5119. Min Act: -0.0000

Data Index: 28157 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4535. Min Act: -0.0000

Data Index: 872484 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4854. Min Act: -0.0000

Data Index: 801257 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4494. Min Act: -0.0000

Data Index: 198757 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4678. Min Act: -0.0000

Data Index: 700839 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3906. Min Act: -0.0000

Data Index: 490866 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3910. Min Act: -0.0000

Data Index: 154247 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1131376 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1331537 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3610. Min Act: -0.0000

Data Index: 764694 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3783. Min Act: -0.0000

Data Index: 726276 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1268047 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3691. Min Act: -0.0000

Data Index: 287914 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1126804 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3430. Min Act: -0.0000

Data Index: 428826 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3293. Min Act: -0.0000

Data Index: 229518 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3611. Min Act: -0.0000

Data Index: 151299 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3375. Min Act: -0.0000

Data Index: 931905 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3301. Min Act: -0.0000

Data Index: 513656 (C4 (Web Text))

Max Activating Token Index: 917