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

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

Neuron 3710 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1261658 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0003

Data Index: 760132 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0110. Min Act: -0.0002

Data Index: 949521 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1157521 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1219913 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0095. Min Act: -0.0003

Data Index: 459887 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0091. Min Act: -0.0003

Data Index: 406619 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0090. Min Act: -0.0002

Data Index: 36539 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0086. Min Act: -0.0002

Data Index: 215376 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1102176 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0089. Min Act: -0.0002

Data Index: 198280 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0086. Min Act: -0.0003

Data Index: 388048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0089. Min Act: -0.0003

Data Index: 305633 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0090. Min Act: -0.0002

Data Index: 180237 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1051328 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1654214 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0083. Min Act: -0.0002

Data Index: 663591 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1214366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0082. Min Act: -0.0002

Data Index: 346776 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1211173 (C4 (Web Text))

Max Activating Token Index: 462