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

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

Neuron 5643 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: 2.3003. Min Range: -2.3003

Max Act: 2.0562. Min Act: -0.0000

Data Index: 657955 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 2.3003. Min Range: -2.3003

Max Act: 2.3003. Min Act: -0.0000

Data Index: 893927 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 2.3003. Min Range: -2.3003

Max Act: 2.1643. Min Act: -0.0000

Data Index: 587096 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 2.3003. Min Range: -2.3003

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1066669 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.3003. Min Range: -2.3003

Max Act: 2.1705. Min Act: -0.0000

Data Index: 1087888 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.9898. Min Act: -0.0000

Data Index: 180433 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.9871. Min Act: -0.0000

Data Index: 1203295 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.8334. Min Act: -0.0000

Data Index: 738340 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1001590 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.7257. Min Act: -0.0000

Data Index: 1165906 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1037551 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.7911. Min Act: -0.0000

Data Index: 1113285 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.7920. Min Act: -0.0000

Data Index: 15520 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.7855. Min Act: -0.0000

Data Index: 129709 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.8565. Min Act: -0.0000

Data Index: 389697 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.7689. Min Act: -0.0000

Data Index: 542690 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.8596. Min Act: -0.0000

Data Index: 302294 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.8781. Min Act: -0.0000

Data Index: 420184 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.9358. Min Act: -0.0000

Data Index: 999931 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 2.3003. Min Range: -2.3003

Max Act: 1.8069. Min Act: -0.0000

Data Index: 623494 (C4 (Web Text))

Max Activating Token Index: 68