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

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

Neuron 4098 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8563. Min Act: -0.0002

Data Index: 781175 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8073. Min Act: -0.0002

Data Index: 1256766 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8734. Min Act: -0.0002

Data Index: 655888 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8394. Min Act: -0.0002

Data Index: 327221 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8595. Min Act: -0.0002

Data Index: 947078 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8510. Min Act: -0.0002

Data Index: 876277 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.7953. Min Act: -0.0002

Data Index: 181464 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.7876. Min Act: -0.0002

Data Index: 1040862 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.7998. Min Act: -0.0002

Data Index: 67816 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.6906. Min Act: -0.0002

Data Index: 264056 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8214. Min Act: -0.0002

Data Index: 547162 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8408. Min Act: -0.0002

Data Index: 29137 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.7834. Min Act: -0.0002

Data Index: 1345310 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.6654. Min Act: -0.0002

Data Index: 634319 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8128. Min Act: -0.0002

Data Index: 362697 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8035. Min Act: -0.0002

Data Index: 824557 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.7839. Min Act: -0.0002

Data Index: 81962 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8501. Min Act: -0.0002

Data Index: 81856 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8494. Min Act: -0.0002

Data Index: 470387 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.7813. Min Act: -0.0002

Data Index: 1079848 (C4 (Web Text))

Max Activating Token Index: 298