Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3000 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1061713 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1101. Min Act: -0.0000

Data Index: 384586 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0000

Data Index: 899090 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1084004 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1121. Min Act: -0.0000

Data Index: 955942 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1030. Min Act: -0.0000

Data Index: 467838 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1045. Min Act: -0.0000

Data Index: 280018 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1027835 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1110. Min Act: -0.0000

Data Index: 985326 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1137722 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1054. Min Act: -0.0000

Data Index: 368614 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1320805 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1031. Min Act: -0.0000

Data Index: 370511 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0975. Min Act: -0.0000

Data Index: 847186 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1356035 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1028. Min Act: -0.0000

Data Index: 746219 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1024. Min Act: -0.0000

Data Index: 345408 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0981. Min Act: -0.0000

Data Index: 20661 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0985. Min Act: -0.0000

Data Index: 293790 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0946. Min Act: -0.0000

Data Index: 372447 (C4 (Web Text))

Max Activating Token Index: 915