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

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

Neuron 3667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1314. Min Act: -0.0003

Data Index: 277045 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1166. Min Act: -0.0003

Data Index: 1255623 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1182. Min Act: -0.0003

Data Index: 221153 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1151. Min Act: -0.0003

Data Index: 403237 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1167. Min Act: -0.0002

Data Index: 942619 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1111. Min Act: -0.0002

Data Index: 303950 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1104. Min Act: -0.0003

Data Index: 24285 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1263133 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1050. Min Act: -0.0003

Data Index: 647521 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1170017 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1072. Min Act: -0.0003

Data Index: 672060 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1026. Min Act: -0.0003

Data Index: 333270 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1020. Min Act: -0.0002

Data Index: 759633 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1007. Min Act: -0.0003

Data Index: 1359102 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0996. Min Act: -0.0002

Data Index: 152171 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0997. Min Act: -0.0003

Data Index: 368460 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1024. Min Act: -0.0003

Data Index: 937161 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0986. Min Act: -0.0003

Data Index: 421531 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0985. Min Act: -0.0003

Data Index: 1332113 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0945. Min Act: -0.0003

Data Index: 1075353 (C4 (Web Text))

Max Activating Token Index: 821