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

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

Neuron 3180 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0002

Data Index: 152999 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1228. Min Act: -0.0002

Data Index: 337003 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1126435 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1174. Min Act: -0.0002

Data Index: 764675 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1121. Min Act: -0.0002

Data Index: 863720 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1152. Min Act: -0.0002

Data Index: 276581 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1179. Min Act: -0.0002

Data Index: 592082 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1137. Min Act: -0.0002

Data Index: 952209 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1125. Min Act: -0.0002

Data Index: 35160 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1046. Min Act: -0.0002

Data Index: 856484 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1075. Min Act: -0.0002

Data Index: 437931 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1078. Min Act: -0.0002

Data Index: 635930 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1066. Min Act: -0.0002

Data Index: 567443 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1012655 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1078. Min Act: -0.0002

Data Index: 713314 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1073. Min Act: -0.0002

Data Index: 411696 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0995. Min Act: -0.0002

Data Index: 477525 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0998. Min Act: -0.0002

Data Index: 520666 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0985. Min Act: -0.0002

Data Index: 711671 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1022. Min Act: -0.0002

Data Index: 681229 (C4 (Web Text))

Max Activating Token Index: 67