Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 153 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0152. Min Act: -0.0006

Data Index: 975816 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1188404 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0120. Min Act: -0.0006

Data Index: 313185 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0120. Min Act: -0.0006

Data Index: 689261 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0119. Min Act: -0.0006

Data Index: 429910 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1255411 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0113. Min Act: -0.0006

Data Index: 17852 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1166870 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0110. Min Act: -0.0006

Data Index: 241382 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0105. Min Act: -0.0006

Data Index: 435029 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0103. Min Act: -0.0006

Data Index: 808866 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0102. Min Act: -0.0006

Data Index: 308639 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1003124 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1153955 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1154987 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0101. Min Act: -0.0006

Data Index: 496154 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0099. Min Act: -0.0006

Data Index: 328230 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0096. Min Act: -0.0006

Data Index: 395155 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0098. Min Act: -0.0006

Data Index: 923059 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1357149 (C4 (Web Text))

Max Activating Token Index: 939