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

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

Neuron 4212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.7032. Min Act: -0.0000

Data Index: 875907 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6488. Min Act: -0.0000

Data Index: 195028 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5869. Min Act: -0.0000

Data Index: 91085 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1213088 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1310072 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5762. Min Act: -0.0000

Data Index: 272 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5565. Min Act: -0.0001

Data Index: 1048918 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5184. Min Act: -0.0001

Data Index: 86927 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5411. Min Act: -0.0000

Data Index: 878430 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1264137 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5020. Min Act: -0.0000

Data Index: 105847 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5155. Min Act: -0.0000

Data Index: 781505 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4649. Min Act: -0.0000

Data Index: 121660 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5081. Min Act: -0.0000

Data Index: 344792 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5271. Min Act: -0.0001

Data Index: 1287192 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5061. Min Act: -0.0000

Data Index: 680136 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5495. Min Act: -0.0001

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1142750 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5162. Min Act: -0.0000

Data Index: 719371 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4608. Min Act: -0.0000

Data Index: 13336 (C4 (Web Text))

Max Activating Token Index: 45