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

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

Neuron 3804 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5946. Min Act: -0.0000

Data Index: 402664 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.6061. Min Act: -0.0000

Data Index: 942407 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5881. Min Act: -0.0000

Data Index: 361148 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4837. Min Act: -0.0000

Data Index: 912972 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4976. Min Act: -0.0000

Data Index: 544523 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4832. Min Act: -0.0000

Data Index: 170113 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5231. Min Act: -0.0000

Data Index: 50596 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5041. Min Act: -0.0000

Data Index: 595596 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4990. Min Act: -0.0000

Data Index: 819937 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4511. Min Act: -0.0000

Data Index: 594066 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4713. Min Act: -0.0000

Data Index: 235503 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4272. Min Act: -0.0000

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4489. Min Act: -0.0000

Data Index: 938967 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4590. Min Act: -0.0000

Data Index: 27678 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1086294 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4670. Min Act: -0.0000

Data Index: 177616 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4570. Min Act: -0.0000

Data Index: 639014 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1199245 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4043. Min Act: -0.0000

Data Index: 664302 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 61