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

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

Neuron 1825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1056596 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6006. Min Act: -0.0000

Data Index: 766711 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1316282 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1046357 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5315. Min Act: -0.0000

Data Index: 454893 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1170560 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1091455 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5191. Min Act: -0.0000

Data Index: 524284 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4648. Min Act: -0.0000

Data Index: 889403 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1063274 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4931. Min Act: -0.0000

Data Index: 979881 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4811. Min Act: -0.0000

Data Index: 111209 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1285620 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1068312 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4603. Min Act: -0.0000

Data Index: 49399 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4670. Min Act: -0.0000

Data Index: 539976 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1230740 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4270. Min Act: -0.0000

Data Index: 890974 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4447. Min Act: -0.0000

Data Index: 907035 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1150964 (C4 (Web Text))

Max Activating Token Index: 722