Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2931 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.7823. Min Act: -0.0001

Data Index: 852044 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6274. Min Act: -0.0001

Data Index: 216344 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6378. Min Act: -0.0001

Data Index: 196362 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5920. Min Act: -0.0001

Data Index: 338559 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5569. Min Act: -0.0001

Data Index: 862504 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5259. Min Act: -0.0001

Data Index: 931164 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5478. Min Act: -0.0001

Data Index: 1283707 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5525. Min Act: -0.0001

Data Index: 1192754 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5433. Min Act: -0.0001

Data Index: 126930 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5249. Min Act: -0.0001

Data Index: 830785 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5298. Min Act: -0.0001

Data Index: 533324 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5160. Min Act: -0.0001

Data Index: 89708 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5102. Min Act: -0.0001

Data Index: 659690 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5410. Min Act: -0.0001

Data Index: 870989 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5625. Min Act: -0.0001

Data Index: 148233 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5192. Min Act: -0.0001

Data Index: 392762 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5324. Min Act: -0.0001

Data Index: 1031583 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5129. Min Act: -0.0001

Data Index: 458807 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1043764 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5093. Min Act: -0.0001

Data Index: 222901 (C4 (Web Text))

Max Activating Token Index: 888