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

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

Neuron 3080 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: 1.8073. Min Range: -1.8073

Max Act: 1.5184. Min Act: -0.0000

Data Index: 504895 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.8073. Min Act: -0.0000

Data Index: 1402619 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1239863 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1210069 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.4061. Min Act: -0.0000

Data Index: 736440 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.4744. Min Act: -0.0000

Data Index: 847191 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.3916. Min Act: -0.0000

Data Index: 19209 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1024516 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.3233. Min Act: -0.0000

Data Index: 161358 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2991. Min Act: -0.0000

Data Index: 262448 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1229395 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1212930 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2335. Min Act: -0.0000

Data Index: 835285 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1449784 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.1465. Min Act: -0.0000

Data Index: 98443 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.3185. Min Act: -0.0000

Data Index: 48427 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1040604 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1183903 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1294331 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.8073. Min Range: -1.8073

Max Act: 1.2132. Min Act: -0.0000

Data Index: 955255 (C4 (Web Text))

Max Activating Token Index: 62