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

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

Neuron 2914 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0001

Data Index: 623689 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1112997 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1321. Min Act: -0.0001

Data Index: 717840 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1235. Min Act: -0.0001

Data Index: 818199 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1307993 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1274. Min Act: -0.0001

Data Index: 417447 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1232. Min Act: -0.0001

Data Index: 310071 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1102. Min Act: -0.0001

Data Index: 879544 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1110. Min Act: -0.0001

Data Index: 370470 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1059. Min Act: -0.0001

Data Index: 513804 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1018725 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1333156 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1013. Min Act: -0.0001

Data Index: 956270 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1120. Min Act: -0.0001

Data Index: 289668 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0941. Min Act: -0.0001

Data Index: 572381 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1011. Min Act: -0.0001

Data Index: 797489 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1099. Min Act: -0.0001

Data Index: 430834 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1011487 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1009. Min Act: -0.0001

Data Index: 226912 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1309888 (C4 (Web Text))

Max Activating Token Index: 134