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

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

Neuron 1180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1589. Min Act: -0.0001

Data Index: 691808 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1272. Min Act: -0.0001

Data Index: 927221 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1208. Min Act: -0.0001

Data Index: 538323 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1184. Min Act: -0.0001

Data Index: 99385 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1193. Min Act: -0.0001

Data Index: 814478 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1161. Min Act: -0.0001

Data Index: 886991 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1301440 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1056. Min Act: -0.0001

Data Index: 437353 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1084. Min Act: -0.0001

Data Index: 951576 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1234472 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1325556 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1297280 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1035. Min Act: -0.0001

Data Index: 38802 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1024. Min Act: -0.0001

Data Index: 135259 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1054. Min Act: -0.0001

Data Index: 404829 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1067. Min Act: -0.0001

Data Index: 141117 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1179937 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1017. Min Act: -0.0001

Data Index: 521326 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1009. Min Act: -0.0001

Data Index: 466117 (C4 (Web Text))

Max Activating Token Index: 352