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

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

Neuron 4517 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: 1.2564. Min Range: -1.2564

Max Act: 1.2564. Min Act: -0.0000

Data Index: 672068 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.2564. Min Range: -1.2564

Max Act: 1.1195. Min Act: -0.0000

Data Index: 449205 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.2564. Min Range: -1.2564

Max Act: 1.0545. Min Act: -0.0000

Data Index: 185676 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1241992 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1076802 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.9123. Min Act: -0.0000

Data Index: 123661 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8867. Min Act: -0.0000

Data Index: 430527 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8944. Min Act: -0.0000

Data Index: 40533 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8418. Min Act: -0.0000

Data Index: 391330 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8248. Min Act: -0.0000

Data Index: 424005 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8765. Min Act: -0.0000

Data Index: 113509 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8655. Min Act: -0.0000

Data Index: 266894 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.7578. Min Act: -0.0000

Data Index: 696338 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1192732 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1147418 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8535. Min Act: -0.0000

Data Index: 382435 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8107. Min Act: -0.0000

Data Index: 491325 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8142. Min Act: -0.0000

Data Index: 151705 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1135398 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.2564. Min Range: -1.2564

Max Act: 0.8446. Min Act: -0.0000

Data Index: 379099 (C4 (Web Text))

Max Activating Token Index: 626