Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 633 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0004

Data Index: 734004 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0118. Min Act: -0.0004

Data Index: 870806 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0113. Min Act: -0.0004

Data Index: 1349000 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0107. Min Act: -0.0004

Data Index: 801815 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0106. Min Act: -0.0004

Data Index: 247261 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0104. Min Act: -0.0004

Data Index: 359498 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0103. Min Act: -0.0004

Data Index: 370098 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0102. Min Act: -0.0004

Data Index: 445130 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0100. Min Act: -0.0004

Data Index: 547299 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1050378 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0101. Min Act: -0.0004

Data Index: 698505 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0100. Min Act: -0.0004

Data Index: 1235216 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0101. Min Act: -0.0004

Data Index: 166480 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0099. Min Act: -0.0004

Data Index: 358306 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0097. Min Act: -0.0004

Data Index: 1121305 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0096. Min Act: -0.0004

Data Index: 1152713 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0095. Min Act: -0.0004

Data Index: 205960 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0096. Min Act: -0.0005

Data Index: 94681 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0095. Min Act: -0.0004

Data Index: 712403 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0095. Min Act: -0.0004

Data Index: 564152 (C4 (Web Text))

Max Activating Token Index: 977