Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.6061. Min Act: -0.0000

Data Index: 305762 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4057. Min Act: -0.0000

Data Index: 842078 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4157. Min Act: -0.0000

Data Index: 435859 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1138495 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2950. Min Act: -0.0000

Data Index: 41294 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2081. Min Act: -0.0000

Data Index: 1271592 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0947. Min Act: -0.0000

Data Index: 1290489 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1143. Min Act: -0.0001

Data Index: 948918 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0276. Min Act: -0.0000

Data Index: 373909 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1246. Min Act: -0.0000

Data Index: 798368 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1656. Min Act: -0.0000

Data Index: 43145 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1243221 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0345. Min Act: -0.0000

Data Index: 605411 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0525. Min Act: -0.0000

Data Index: 490483 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1186681 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0338. Min Act: -0.0000

Data Index: 146641 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9990. Min Act: -0.0000

Data Index: 935072 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9010. Min Act: -0.0000

Data Index: 30178 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9668. Min Act: -0.0000

Data Index: 954122 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1105225 (C4 (Web Text))

Max Activating Token Index: 20