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

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

Neuron 3747 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7914. Min Range: -3.7914

Max Act: 3.7914. Min Act: -0.0000

Data Index: 669112 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.7914. Min Range: -3.7914

Max Act: 3.2644. Min Act: -0.0000

Data Index: 566831 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 3.7914. Min Range: -3.7914

Max Act: 3.3818. Min Act: -0.0000

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.9738. Min Act: -0.0000

Data Index: 303734 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.8464. Min Act: -0.0000

Data Index: 356375 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.8606. Min Act: -0.0000

Data Index: 970994 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.7726. Min Act: -0.0000

Data Index: 702970 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.7853. Min Act: -0.0000

Data Index: 1086541 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.8840. Min Act: -0.0000

Data Index: 1359482 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.7487. Min Act: -0.0000

Data Index: 846670 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.5722. Min Act: -0.0000

Data Index: 344531 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.4788. Min Act: -0.0000

Data Index: 419269 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.4922. Min Act: -0.0000

Data Index: 1275801 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.4578. Min Act: -0.0000

Data Index: 710403 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.4300. Min Act: -0.0000

Data Index: 1061826 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.5581. Min Act: -0.0000

Data Index: 447468 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.4231. Min Act: -0.0000

Data Index: 1138788 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1570507 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.3576. Min Act: -0.0000

Data Index: 981062 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 3.7914. Min Range: -3.7914

Max Act: 2.3116. Min Act: -0.0000

Data Index: 729924 (C4 (Web Text))

Max Activating Token Index: 809