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

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

Neuron 4847 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1028135 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.9239. Min Act: -0.0000

Data Index: 212463 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.9223. Min Act: -0.0000

Data Index: 163748 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8741. Min Act: -0.0000

Data Index: 885276 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8540. Min Act: -0.0000

Data Index: 178053 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7947. Min Act: -0.0000

Data Index: 534119 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8025. Min Act: -0.0000

Data Index: 295373 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7937. Min Act: -0.0000

Data Index: 457891 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7925. Min Act: -0.0000

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1259651 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7320. Min Act: -0.0000

Data Index: 151912 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7526. Min Act: -0.0000

Data Index: 413328 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7218. Min Act: -0.0000

Data Index: 632675 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7496. Min Act: -0.0000

Data Index: 546300 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1309915 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6725. Min Act: -0.0000

Data Index: 797530 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7158. Min Act: -0.0000

Data Index: 679857 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7149. Min Act: -0.0000

Data Index: 5095 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7143. Min Act: -0.0000

Data Index: 185183 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.7135. Min Act: -0.0000

Data Index: 11004 (C4 (Web Text))

Max Activating Token Index: 696