Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 474 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0006

Data Index: 657957 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0134. Min Act: -0.0006

Data Index: 355044 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1351349 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1084084 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0123. Min Act: -0.0006

Data Index: 614978 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0112. Min Act: -0.0006

Data Index: 352028 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0111. Min Act: -0.0006

Data Index: 23013 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1257396 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0113. Min Act: -0.0006

Data Index: 978655 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1202276 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1257578 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0109. Min Act: -0.0006

Data Index: 723703 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1171489 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0110. Min Act: -0.0006

Data Index: 359119 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0111. Min Act: -0.0006

Data Index: 489458 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0109. Min Act: -0.0006

Data Index: 564239 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0106. Min Act: -0.0006

Data Index: 621008 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0109. Min Act: -0.0006

Data Index: 965573 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0100. Min Act: -0.0006

Data Index: 458105 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1150773 (C4 (Web Text))

Max Activating Token Index: 82