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

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

Neuron 3323 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.9628. Min Act: -0.0000

Data Index: 509700 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.8352. Min Act: -0.0000

Data Index: 14326 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7609. Min Act: -0.0000

Data Index: 461150 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.8519. Min Act: -0.0000

Data Index: 310337 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7991. Min Act: -0.0000

Data Index: 974157 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7329. Min Act: -0.0000

Data Index: 510423 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7896. Min Act: -0.0000

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1158053 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.8079. Min Act: -0.0000

Data Index: 9629 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1024787 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.6922. Min Act: -0.0000

Data Index: 943536 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.6669. Min Act: -0.0000

Data Index: 22505 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1099571 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7227. Min Act: -0.0000

Data Index: 540835 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7412. Min Act: -0.0000

Data Index: 431125 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.6764. Min Act: -0.0000

Data Index: 9186 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.6820. Min Act: -0.0000

Data Index: 2161 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7181. Min Act: -0.0000

Data Index: 36012 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.6718. Min Act: -0.0000

Data Index: 448340 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.9628. Min Range: -0.9628

Max Act: 0.7394. Min Act: -0.0000

Data Index: 739136 (C4 (Web Text))

Max Activating Token Index: 815