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

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

Neuron 1555 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.3679. Min Act: -0.0000

Data Index: 830031 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.3592. Min Act: -0.0000

Data Index: 90062 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.3109. Min Act: -0.0000

Data Index: 686654 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.3300. Min Act: -0.0000

Data Index: 695000 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.2802. Min Act: -0.0000

Data Index: 443525 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.2297. Min Act: -0.0000

Data Index: 111130 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.2546. Min Act: -0.0000

Data Index: 409825 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.2274. Min Act: -0.0000

Data Index: 613088 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1213287 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0904. Min Act: -0.0000

Data Index: 422300 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1042334 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0894. Min Act: -0.0000

Data Index: 301242 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0640. Min Act: -0.0000

Data Index: 859797 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0774. Min Act: -0.0000

Data Index: 655817 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1028. Min Act: -0.0000

Data Index: 320601 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1240860 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1011. Min Act: -0.0000

Data Index: 440302 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0534. Min Act: -0.0000

Data Index: 281922 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0531. Min Act: -0.0000

Data Index: 949915 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0412. Min Act: -0.0000

Data Index: 492066 (C4 (Web Text))

Max Activating Token Index: 197