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

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

Neuron 4050 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.5625. Min Act: -0.0002

Data Index: 623954 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.4481. Min Act: -0.0002

Data Index: 1188542 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.4567. Min Act: -0.0002

Data Index: 425143 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.5124. Min Act: -0.0002

Data Index: 977188 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.3215. Min Act: -0.0002

Data Index: 1174624 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2901. Min Act: -0.0002

Data Index: 1063484 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.5733. Min Act: -0.0002

Data Index: 846998 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.5512. Min Act: -0.0002

Data Index: 374103 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2838. Min Act: -0.0002

Data Index: 1135276 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1501. Min Act: -0.0002

Data Index: 567134 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2183. Min Act: -0.0002

Data Index: 448299 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2622. Min Act: -0.0002

Data Index: 778878 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0805. Min Act: -0.0002

Data Index: 582578 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2891. Min Act: -0.0002

Data Index: 307231 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2997. Min Act: -0.0002

Data Index: 721273 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.3381. Min Act: -0.0002

Data Index: 1052460 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2663. Min Act: -0.0002

Data Index: 237788 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2169. Min Act: -0.0002

Data Index: 639634 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2394. Min Act: -0.0002

Data Index: 849916 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1323. Min Act: -0.0002

Data Index: 80409 (C4 (Web Text))

Max Activating Token Index: 679