Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2685 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.2743. Min Act: -0.0002

Data Index: 366091 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.1365. Min Act: -0.0002

Data Index: 759600 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0372. Min Act: -0.0001

Data Index: 326273 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0856. Min Act: -0.0002

Data Index: 1031043 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0863. Min Act: -0.0001

Data Index: 130007 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0543. Min Act: -0.0002

Data Index: 614058 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0383. Min Act: -0.0002

Data Index: 113929 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0274. Min Act: -0.0002

Data Index: 566387 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9928. Min Act: -0.0002

Data Index: 101686 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9909. Min Act: -0.0002

Data Index: 1302202 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0208. Min Act: -0.0002

Data Index: 1088684 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9339. Min Act: -0.0001

Data Index: 743484 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9834. Min Act: -0.0002

Data Index: 242623 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0163. Min Act: -0.0002

Data Index: 658189 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9396. Min Act: -0.0001

Data Index: 465651 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9473. Min Act: -0.0002

Data Index: 14183 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9914. Min Act: -0.0002

Data Index: 1213881 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9564. Min Act: -0.0002

Data Index: 526818 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.8852. Min Act: -0.0002

Data Index: 1287392 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9615. Min Act: -0.0002

Data Index: 1043669 (C4 (Web Text))

Max Activating Token Index: 927