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

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

Neuron 2084 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0002

Data Index: 243956 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1250139 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1236970 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0117. Min Act: -0.0002

Data Index: 460073 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0002

Data Index: 707226 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0002

Data Index: 378162 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1112352 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 105087 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1038673 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 971390 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0002

Data Index: 501443 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0002

Data Index: 317830 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 743449 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0002

Data Index: 777241 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0002

Data Index: 360205 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0002

Data Index: 203791 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0002

Data Index: 713909 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1022762 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0002

Data Index: 204712 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0002

Data Index: 412078 (C4 (Web Text))

Max Activating Token Index: 160