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

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

Neuron 44 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1242. Min Act: -0.0000

Data Index: 704971 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0000

Data Index: 423241 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1289. Min Act: -0.0000

Data Index: 435314 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1229. Min Act: -0.0000

Data Index: 8771 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1179. Min Act: -0.0000

Data Index: 657937 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1123. Min Act: -0.0000

Data Index: 635995 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1032779 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1173. Min Act: -0.0000

Data Index: 670893 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1068. Min Act: -0.0000

Data Index: 994720 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1254276 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1258468 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1051. Min Act: -0.0000

Data Index: 754195 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1144042 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1028. Min Act: -0.0000

Data Index: 481932 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1092. Min Act: -0.0000

Data Index: 127252 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1088. Min Act: -0.0000

Data Index: 532361 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0907. Min Act: -0.0000

Data Index: 997932 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1079. Min Act: -0.0000

Data Index: 945929 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0969. Min Act: -0.0000

Data Index: 748614 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1073. Min Act: -0.0000

Data Index: 289136 (C4 (Web Text))

Max Activating Token Index: 723