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

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

Neuron 1445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2805. Min Act: -0.0001

Data Index: 508962 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2865. Min Act: -0.0001

Data Index: 1293183 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.4214. Min Act: -0.0001

Data Index: 1222487 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.4120. Min Act: -0.0001

Data Index: 645531 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.3903. Min Act: -0.0001

Data Index: 344148 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.3783. Min Act: -0.0001

Data Index: 547197 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.3083. Min Act: -0.0001

Data Index: 755634 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2955. Min Act: -0.0001

Data Index: 43261 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2583. Min Act: -0.0001

Data Index: 1065342 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2508. Min Act: -0.0001

Data Index: 1204725 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2414. Min Act: -0.0000

Data Index: 727954 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.3000. Min Act: -0.0001

Data Index: 459329 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1819. Min Act: -0.0001

Data Index: 450532 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2751. Min Act: -0.0001

Data Index: 1068883 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2860. Min Act: -0.0001

Data Index: 1186884 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1657. Min Act: -0.0001

Data Index: 1045446 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1591. Min Act: -0.0001

Data Index: 242147 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1745. Min Act: -0.0000

Data Index: 34145 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2053. Min Act: -0.0001

Data Index: 169952 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1608. Min Act: -0.0001

Data Index: 316428 (C4 (Web Text))

Max Activating Token Index: 694