Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5453 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.5836. Min Range: -6.5836

Max Act: 6.5836. Min Act: -0.0000

Data Index: 661194 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 6.5836. Min Range: -6.5836

Max Act: 6.4621. Min Act: -0.0000

Data Index: 239033 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 6.5836. Min Range: -6.5836

Max Act: 6.1227. Min Act: -0.0000

Data Index: 429571 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 6.5836. Min Range: -6.5836

Max Act: 5.8563. Min Act: -0.0000

Data Index: 580069 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 6.5836. Min Range: -6.5836

Max Act: 5.8888. Min Act: -0.0000

Data Index: 435221 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 6.5836. Min Range: -6.5836

Max Act: 5.3394. Min Act: -0.0000

Data Index: 674070 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 6.5836. Min Range: -6.5836

Max Act: 5.1837. Min Act: -0.0000

Data Index: 552774 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 6.5836. Min Range: -6.5836

Max Act: 5.2976. Min Act: -0.0000

Data Index: 601749 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 6.5836. Min Range: -6.5836

Max Act: 5.0337. Min Act: -0.0000

Data Index: 563704 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.9510. Min Act: -0.0000

Data Index: 664068 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.6335. Min Act: -0.0000

Data Index: 670911 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.5781. Min Act: -0.0000

Data Index: 896685 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.5051. Min Act: -0.0000

Data Index: 458086 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.4557. Min Act: -0.0000

Data Index: 947456 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.4074. Min Act: 0.0000

Data Index: 1199160 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.3835. Min Act: -0.0000

Data Index: 1208813 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.3238. Min Act: -0.0000

Data Index: 436091 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 6.5836. Min Range: -6.5836

Max Act: 3.9691. Min Act: -0.0000

Data Index: 1313132 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 6.5836. Min Range: -6.5836

Max Act: 4.2459. Min Act: -0.0000

Data Index: 1191361 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 6.5836. Min Range: -6.5836

Max Act: 3.9690. Min Act: -0.0000

Data Index: 1125486 (C4 (Web Text))

Max Activating Token Index: 376