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

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

Neuron 146 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: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1089988 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1157. Min Act: -0.0000

Data Index: 209144 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0988. Min Act: -0.0001

Data Index: 749504 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0946. Min Act: -0.0001

Data Index: 242973 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0889. Min Act: -0.0000

Data Index: 854409 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1127037 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0882. Min Act: -0.0001

Data Index: 669885 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0839. Min Act: -0.0001

Data Index: 406672 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1259681 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0886. Min Act: -0.0001

Data Index: 646778 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0884. Min Act: -0.0001

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0835. Min Act: -0.0001

Data Index: 776485 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1354554 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0829. Min Act: -0.0001

Data Index: 742695 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0857. Min Act: -0.0001

Data Index: 374972 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0809. Min Act: -0.0000

Data Index: 151085 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0809. Min Act: -0.0000

Data Index: 185784 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0831. Min Act: -0.0000

Data Index: 770690 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0799. Min Act: -0.0001

Data Index: 514221 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1114281 (C4 (Web Text))

Max Activating Token Index: 600