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

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

Neuron 3599 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1245. Min Range: -1.1245

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1275144 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.1245. Min Range: -1.1245

Max Act: 1.1002. Min Act: -0.0000

Data Index: 737185 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 1.1245. Min Range: -1.1245

Max Act: 1.0881. Min Act: -0.0000

Data Index: 445700 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1027218 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.9144. Min Act: -0.0000

Data Index: 59837 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.9572. Min Act: -0.0000

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8806. Min Act: -0.0000

Data Index: 431600 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.9078. Min Act: -0.0000

Data Index: 670756 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1077046 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8592. Min Act: -0.0000

Data Index: 254740 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8524. Min Act: -0.0000

Data Index: 462057 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8352. Min Act: -0.0000

Data Index: 767579 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8129. Min Act: -0.0000

Data Index: 40800 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1199783 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1179479 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8037. Min Act: -0.0000

Data Index: 326791 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1341491 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.8108. Min Act: -0.0000

Data Index: 351807 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.1245. Min Range: -1.1245

Max Act: 0.7906. Min Act: -0.0000

Data Index: 524700 (C4 (Web Text))

Max Activating Token Index: 307