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

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

Neuron 5077 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6216. Min Act: -0.0000

Data Index: 25154 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5647. Min Act: -0.0000

Data Index: 630458 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6102. Min Act: -0.0000

Data Index: 250448 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1104558 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5658. Min Act: -0.0000

Data Index: 83277 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5659. Min Act: -0.0000

Data Index: 65749 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5249. Min Act: -0.0000

Data Index: 647586 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5229. Min Act: -0.0000

Data Index: 115947 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4960. Min Act: -0.0000

Data Index: 325523 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4938. Min Act: -0.0000

Data Index: 984668 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1209457 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4692. Min Act: -0.0000

Data Index: 165201 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4582. Min Act: -0.0000

Data Index: 125777 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5073. Min Act: -0.0000

Data Index: 941078 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1238653 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4959. Min Act: -0.0000

Data Index: 313510 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4744. Min Act: -0.0000

Data Index: 494543 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4829. Min Act: -0.0000

Data Index: 113627 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4552. Min Act: -0.0000

Data Index: 159547 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4713. Min Act: -0.0000

Data Index: 720685 (C4 (Web Text))

Max Activating Token Index: 622