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

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

Neuron 908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8385. Min Act: -0.0002

Data Index: 990967 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8357. Min Act: -0.0002

Data Index: 1357927 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8235. Min Act: -0.0002

Data Index: 28711 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8243. Min Act: -0.0002

Data Index: 994313 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8377. Min Act: -0.0002

Data Index: 693662 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7875. Min Act: -0.0002

Data Index: 501311 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7550. Min Act: -0.0002

Data Index: 212383 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7799. Min Act: -0.0002

Data Index: 630797 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7887. Min Act: -0.0002

Data Index: 933502 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7874. Min Act: -0.0002

Data Index: 1135527 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8058. Min Act: -0.0002

Data Index: 1108445 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7828. Min Act: -0.0002

Data Index: 327606 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7634. Min Act: -0.0002

Data Index: 1172257 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7606. Min Act: -0.0002

Data Index: 1351068 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7603. Min Act: -0.0002

Data Index: 311455 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8098. Min Act: -0.0002

Data Index: 58106 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7322. Min Act: -0.0002

Data Index: 399065 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7279. Min Act: -0.0002

Data Index: 1316295 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6635. Min Act: -0.0002

Data Index: 1101192 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6855. Min Act: -0.0002

Data Index: 709112 (C4 (Web Text))

Max Activating Token Index: 218