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

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

Neuron 972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1161234 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1233530 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1284. Min Act: -0.0001

Data Index: 724349 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1258. Min Act: -0.0000

Data Index: 691168 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1077714 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1092. Min Act: -0.0001

Data Index: 691791 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1166. Min Act: -0.0000

Data Index: 269747 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1123. Min Act: -0.0001

Data Index: 156831 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1243522 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1111. Min Act: -0.0001

Data Index: 509115 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1075. Min Act: -0.0000

Data Index: 496820 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1072. Min Act: -0.0001

Data Index: 219731 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1082297 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1109859 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1014. Min Act: -0.0001

Data Index: 125837 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1349375 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1085. Min Act: -0.0001

Data Index: 114718 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1120226 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0990. Min Act: -0.0001

Data Index: 350027 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0976. Min Act: -0.0001

Data Index: 684994 (C4 (Web Text))

Max Activating Token Index: 269