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

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

Neuron 1249 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: 0.9721. Min Range: -0.9721

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1117362 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.9417. Min Act: -0.0000

Data Index: 959862 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.9275. Min Act: -0.0000

Data Index: 713630 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1175353 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.9644. Min Act: -0.0000

Data Index: 936377 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.8315. Min Act: -0.0000

Data Index: 787505 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.8083. Min Act: -0.0000

Data Index: 919639 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7205. Min Act: -0.0000

Data Index: 678226 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1209439 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1085775 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7266. Min Act: -0.0000

Data Index: 197394 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1049060 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7096. Min Act: -0.0000

Data Index: 61141 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7072. Min Act: -0.0000

Data Index: 683831 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1217432 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7013. Min Act: -0.0000

Data Index: 704768 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1084752 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6737. Min Act: -0.0000

Data Index: 353150 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7032. Min Act: -0.0000

Data Index: 421412 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6700. Min Act: -0.0000

Data Index: 428588 (C4 (Web Text))

Max Activating Token Index: 474