Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 128 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0003

Data Index: 670487 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0003

Data Index: 342198 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0003

Data Index: 653597 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0003

Data Index: 128731 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1046601 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1080514 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0003

Data Index: 75794 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0003

Data Index: 105430 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1140362 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0003

Data Index: 671450 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0003

Data Index: 107093 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0003

Data Index: 239124 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0003

Data Index: 838353 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1042617 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1227935 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0103. Min Act: -0.0003

Data Index: 61601 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0104. Min Act: -0.0003

Data Index: 30529 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0003

Data Index: 323174 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0104. Min Act: -0.0003

Data Index: 282709 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0104. Min Act: -0.0003

Data Index: 511869 (C4 (Web Text))

Max Activating Token Index: 220