Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1718 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0001

Data Index: 460905 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2251. Min Act: -0.0000

Data Index: 15839 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2099. Min Act: -0.0000

Data Index: 258714 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2115. Min Act: -0.0001

Data Index: 67558 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2030. Min Act: -0.0000

Data Index: 895758 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1358830 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1261571 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1272336 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1826. Min Act: -0.0000

Data Index: 55498 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1164941 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1800. Min Act: -0.0001

Data Index: 758130 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1870. Min Act: -0.0000

Data Index: 800957 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1931. Min Act: -0.0001

Data Index: 189631 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1857. Min Act: -0.0001

Data Index: 700697 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1108451 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1768. Min Act: -0.0000

Data Index: 199927 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1765. Min Act: -0.0000

Data Index: 946094 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1770. Min Act: -0.0001

Data Index: 198673 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1693. Min Act: -0.0000

Data Index: 392875 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1877. Min Act: -0.0000

Data Index: 299653 (C4 (Web Text))

Max Activating Token Index: 952