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

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

Neuron 3932 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7151. Min Range: -2.7151

Max Act: 2.7151. Min Act: -0.0000

Data Index: 227264 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 2.7151. Min Range: -2.7151

Max Act: 2.2750. Min Act: -0.0000

Data Index: 212487 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 2.7151. Min Range: -2.7151

Max Act: 2.2772. Min Act: -0.0000

Data Index: 801866 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 2.7151. Min Range: -2.7151

Max Act: 2.1883. Min Act: -0.0000

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.7151. Min Range: -2.7151

Max Act: 2.1455. Min Act: -0.0000

Data Index: 692713 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.9714. Min Act: -0.0000

Data Index: 1140994 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.9284. Min Act: -0.0000

Data Index: 254889 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 2.7151. Min Range: -2.7151

Max Act: 2.1267. Min Act: -0.0000

Data Index: 1234603 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.7232. Min Act: -0.0000

Data Index: 814280 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.8077. Min Act: -0.0000

Data Index: 389282 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.7011. Min Act: -0.0000

Data Index: 1239889 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.7521. Min Act: -0.0000

Data Index: 324378 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.6242. Min Act: -0.0000

Data Index: 808986 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1305167 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.8007. Min Act: -0.0000

Data Index: 177513 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.8035. Min Act: -0.0000

Data Index: 1039778 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.7891. Min Act: -0.0000

Data Index: 1189172 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.6937. Min Act: -0.0000

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.4975. Min Act: -0.0000

Data Index: 628161 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 2.7151. Min Range: -2.7151

Max Act: 1.5194. Min Act: -0.0000

Data Index: 171996 (C4 (Web Text))

Max Activating Token Index: 679