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

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

Neuron 1125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0261. Min Range: -1.0261

Max Act: 1.0209. Min Act: -0.0000

Data Index: 27667 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 1.0261. Min Range: -1.0261

Max Act: 1.0261. Min Act: -0.0000

Data Index: 733532 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.9068. Min Act: -0.0000

Data Index: 577565 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8647. Min Act: -0.0000

Data Index: 692433 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1133565 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8216. Min Act: -0.0000

Data Index: 883609 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8801. Min Act: -0.0000

Data Index: 458631 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8255. Min Act: -0.0000

Data Index: 267177 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1309683 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6733. Min Act: -0.0000

Data Index: 108791 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7309. Min Act: -0.0000

Data Index: 319315 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6879. Min Act: -0.0000

Data Index: 985693 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1173645 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6354. Min Act: -0.0000

Data Index: 729869 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6194. Min Act: -0.0000

Data Index: 600156 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1037970 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1356411 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.5909. Min Act: -0.0000

Data Index: 898729 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6060. Min Act: -0.0000

Data Index: 585764 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1084963 (C4 (Web Text))

Max Activating Token Index: 992