Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 756 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1772. Min Act: -0.0001

Data Index: 360586 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1166070 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1360. Min Act: -0.0001

Data Index: 665407 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1290. Min Act: -0.0001

Data Index: 613586 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1285. Min Act: -0.0001

Data Index: 671 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1274. Min Act: -0.0001

Data Index: 43201 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1275. Min Act: -0.0001

Data Index: 125201 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1307. Min Act: -0.0001

Data Index: 3259 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1203. Min Act: -0.0001

Data Index: 46467 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1179. Min Act: -0.0001

Data Index: 265300 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1199. Min Act: -0.0001

Data Index: 438735 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1090295 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1140. Min Act: -0.0001

Data Index: 227709 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1139. Min Act: -0.0001

Data Index: 874738 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1157. Min Act: -0.0001

Data Index: 428779 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1113. Min Act: -0.0001

Data Index: 618203 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1195. Min Act: -0.0001

Data Index: 986915 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1271854 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1117. Min Act: -0.0001

Data Index: 759017 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1223854 (C4 (Web Text))

Max Activating Token Index: 167