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

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

Neuron 770 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: 0.1228. Min Range: -0.1228

Max Act: 0.1228. Min Act: -0.0001

Data Index: 946689 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1112268 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1122. Min Act: -0.0001

Data Index: 418601 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1147. Min Act: -0.0001

Data Index: 507267 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1214726 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1085. Min Act: -0.0001

Data Index: 550395 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1057. Min Act: -0.0001

Data Index: 563829 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1005. Min Act: -0.0001

Data Index: 548174 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0927. Min Act: -0.0001

Data Index: 488569 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1104. Min Act: -0.0001

Data Index: 987773 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1014374 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1008. Min Act: -0.0001

Data Index: 299727 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1020. Min Act: -0.0001

Data Index: 393332 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1149004 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0937. Min Act: -0.0001

Data Index: 56465 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0848. Min Act: -0.0001

Data Index: 482734 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1232829 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1057894 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0924. Min Act: -0.0001

Data Index: 469875 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0924. Min Act: -0.0001

Data Index: 247725 (C4 (Web Text))

Max Activating Token Index: 479