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

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

Neuron 2173 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0694. Min Range: -1.0694

Max Act: 1.0694. Min Act: -0.0000

Data Index: 389593 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9953. Min Act: -0.0000

Data Index: 323635 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9686. Min Act: -0.0000

Data Index: 502678 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9498. Min Act: -0.0000

Data Index: 942375 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8522. Min Act: -0.0000

Data Index: 393620 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8339. Min Act: -0.0000

Data Index: 799733 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8236. Min Act: -0.0000

Data Index: 882013 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1010697 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1288139 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7565. Min Act: -0.0000

Data Index: 648658 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7997. Min Act: -0.0000

Data Index: 93535 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1281099 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1329612 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1148060 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7122. Min Act: -0.0000

Data Index: 406468 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7374. Min Act: -0.0000

Data Index: 104721 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7117. Min Act: -0.0000

Data Index: 935333 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7055. Min Act: -0.0000

Data Index: 608970 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7248. Min Act: -0.0000

Data Index: 464684 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.6759. Min Act: -0.0000

Data Index: 956239 (C4 (Web Text))

Max Activating Token Index: 820