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

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

Neuron 3906 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1208644 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1327426 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1024. Min Act: -0.0000

Data Index: 532410 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1027. Min Act: -0.0001

Data Index: 570346 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0991. Min Act: -0.0001

Data Index: 737791 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0966. Min Act: -0.0000

Data Index: 949536 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0914. Min Act: -0.0000

Data Index: 738134 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0943. Min Act: -0.0000

Data Index: 647104 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0962. Min Act: -0.0000

Data Index: 609981 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0884. Min Act: -0.0001

Data Index: 303604 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0890. Min Act: -0.0000

Data Index: 789373 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0889. Min Act: -0.0001

Data Index: 189412 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0915. Min Act: -0.0000

Data Index: 10170 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0875. Min Act: -0.0000

Data Index: 662140 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0889. Min Act: -0.0001

Data Index: 121323 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0885. Min Act: -0.0001

Data Index: 277828 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0842. Min Act: -0.0000

Data Index: 892898 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0871. Min Act: -0.0000

Data Index: 769810 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0867. Min Act: -0.0001

Data Index: 566395 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1130254 (C4 (Web Text))

Max Activating Token Index: 812