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

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

Neuron 2711 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: 1.5068. Min Range: -1.5068

Max Act: 1.5068. Min Act: -0.0000

Data Index: 128837 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9774. Min Act: -0.0000

Data Index: 42396 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9590. Min Act: -0.0000

Data Index: 365786 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1108906 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7322. Min Act: -0.0000

Data Index: 777489 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8614. Min Act: -0.0000

Data Index: 797577 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1251899 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8197. Min Act: -0.0000

Data Index: 318139 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8427. Min Act: -0.0000

Data Index: 8402 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8415. Min Act: -0.0000

Data Index: 600839 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7981. Min Act: -0.0000

Data Index: 724170 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8019. Min Act: -0.0000

Data Index: 46034 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1350003 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7669. Min Act: -0.0000

Data Index: 968231 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7642. Min Act: -0.0000

Data Index: 591591 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7541. Min Act: -0.0000

Data Index: 660613 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.8065. Min Act: -0.0000

Data Index: 574017 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7956. Min Act: -0.0000

Data Index: 871206 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7428. Min Act: -0.0000

Data Index: 611362 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.7641. Min Act: -0.0000

Data Index: 537630 (C4 (Web Text))

Max Activating Token Index: 98