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

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

Neuron 5044 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1077733 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6055. Min Act: -0.0000

Data Index: 861405 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6197. Min Act: -0.0000

Data Index: 554964 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6057. Min Act: -0.0000

Data Index: 527542 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1063088 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1126489 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6174. Min Act: -0.0000

Data Index: 726313 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5691. Min Act: -0.0000

Data Index: 617318 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5408. Min Act: -0.0000

Data Index: 493915 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5557. Min Act: -0.0000

Data Index: 391879 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5647. Min Act: -0.0000

Data Index: 206695 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5601. Min Act: -0.0000

Data Index: 103115 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5590. Min Act: -0.0000

Data Index: 72722 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1017141 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5122. Min Act: -0.0000

Data Index: 858417 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1120581 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5200. Min Act: -0.0000

Data Index: 83484 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5055. Min Act: -0.0000

Data Index: 989569 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4862. Min Act: -0.0000

Data Index: 471393 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5012. Min Act: -0.0000

Data Index: 129773 (C4 (Web Text))

Max Activating Token Index: 247