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

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

Neuron 1154 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1240730 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.0904. Min Act: 0.0000

Data Index: 1033359 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1097836 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8791. Min Act: -0.0000

Data Index: 470107 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8326. Min Act: 0.0000

Data Index: 1013338 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1190629 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1239709 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8482. Min Act: -0.0000

Data Index: 389785 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8299. Min Act: 0.0000

Data Index: 356902 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.8552. Min Act: -0.0000

Data Index: 968875 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7996. Min Act: -0.0000

Data Index: 584536 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7899. Min Act: -0.0000

Data Index: 927697 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7703. Min Act: -0.0000

Data Index: 164531 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7778. Min Act: -0.0000

Data Index: 426353 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7391. Min Act: -0.0000

Data Index: 281937 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1228086 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1306344 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1101652 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7358. Min Act: -0.0000

Data Index: 846300 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.2634. Min Range: -1.2634

Max Act: 0.7139. Min Act: -0.0000

Data Index: 481248 (C4 (Web Text))

Max Activating Token Index: 339