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

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

Neuron 4113 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: 0.0122. Min Range: -0.0122

Max Act: 0.0122. Min Act: -0.0002

Data Index: 657099 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1071193 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0120. Min Act: -0.0002

Data Index: 247094 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0120. Min Act: -0.0002

Data Index: 7332 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1018983 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0118. Min Act: -0.0002

Data Index: 786266 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0117. Min Act: -0.0002

Data Index: 203720 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1113937 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0117. Min Act: -0.0002

Data Index: 230187 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0117. Min Act: -0.0002

Data Index: 713023 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0117. Min Act: -0.0002

Data Index: 312979 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1183745 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0116. Min Act: -0.0002

Data Index: 325204 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1057843 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1190504 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1146785 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0114. Min Act: -0.0002

Data Index: 456940 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0114. Min Act: -0.0002

Data Index: 730408 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1052616 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0114. Min Act: -0.0002

Data Index: 461472 (C4 (Web Text))

Max Activating Token Index: 81