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

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

Neuron 3462 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.6227. Min Act: -0.0000

Data Index: 1533674 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.6045. Min Act: -0.0000

Data Index: 349354 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.4206. Min Act: -0.0000

Data Index: 752588 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.3531. Min Act: -0.0000

Data Index: 993847 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.4190. Min Act: -0.0000

Data Index: 201679 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1090174 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.3545. Min Act: -0.0000

Data Index: 662697 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2309. Min Act: -0.0000

Data Index: 197726 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.3051. Min Act: -0.0000

Data Index: 893282 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.3719. Min Act: -0.0000

Data Index: 10571 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1118366 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2907. Min Act: -0.0000

Data Index: 960833 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2668. Min Act: -0.0000

Data Index: 311934 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2846. Min Act: -0.0000

Data Index: 536499 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2621. Min Act: -0.0000

Data Index: 82645 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2420. Min Act: -0.0000

Data Index: 842571 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2294. Min Act: 0.0000

Data Index: 593823 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.1631. Min Act: -0.0000

Data Index: 673257 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.4014. Min Act: -0.0000

Data Index: 493745 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.6227. Min Range: -1.6227

Max Act: 1.2184. Min Act: -0.0000

Data Index: 583835 (C4 (Web Text))

Max Activating Token Index: 452