Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1308 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1126. Min Act: 0.0001

Data Index: 557988 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1259498 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1188. Min Act: -0.0001

Data Index: 573779 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1148. Min Act: -0.0002

Data Index: 45577 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1106583 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1043980 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1065. Min Act: -0.0001

Data Index: 358670 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1099. Min Act: -0.0001

Data Index: 784940 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1060. Min Act: -0.0002

Data Index: 842939 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1165347 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1323725 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1103. Min Act: -0.0002

Data Index: 985848 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1174211 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1031. Min Act: -0.0001

Data Index: 77853 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1068. Min Act: -0.0001

Data Index: 657976 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1053. Min Act: -0.0001

Data Index: 648049 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1057. Min Act: -0.0001

Data Index: 429109 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1047. Min Act: -0.0002

Data Index: 394815 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1148650 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1033770 (C4 (Web Text))

Max Activating Token Index: 436