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

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

Neuron 1626 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: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0001

Data Index: 352217 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1201. Min Act: -0.0001

Data Index: 961971 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1196. Min Act: -0.0001

Data Index: 41361 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1196. Min Act: -0.0001

Data Index: 707388 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1218. Min Act: -0.0001

Data Index: 807300 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1065. Min Act: -0.0001

Data Index: 687589 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1217703 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1102008 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1109033 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1086. Min Act: -0.0001

Data Index: 621977 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1101. Min Act: -0.0001

Data Index: 292953 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1081. Min Act: -0.0001

Data Index: 755947 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0993. Min Act: -0.0001

Data Index: 925032 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1067. Min Act: -0.0001

Data Index: 433312 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1028900 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1067. Min Act: -0.0001

Data Index: 964003 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1067. Min Act: -0.0001

Data Index: 79095 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1059. Min Act: -0.0001

Data Index: 873274 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1048. Min Act: -0.0001

Data Index: 613968 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1017. Min Act: -0.0001

Data Index: 537166 (C4 (Web Text))

Max Activating Token Index: 138