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

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

Neuron 3785 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: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0003

Data Index: 409764 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0146. Min Act: -0.0002

Data Index: 841435 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0133. Min Act: -0.0002

Data Index: 758922 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0130. Min Act: -0.0002

Data Index: 52033 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0129. Min Act: -0.0003

Data Index: 127915 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0125. Min Act: -0.0002

Data Index: 583966 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0127. Min Act: -0.0002

Data Index: 237196 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0122. Min Act: -0.0003

Data Index: 198865 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0120. Min Act: -0.0003

Data Index: 775109 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0120. Min Act: -0.0002

Data Index: 914799 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0117. Min Act: -0.0002

Data Index: 162214 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1341362 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0115. Min Act: -0.0002

Data Index: 501865 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0112. Min Act: -0.0002

Data Index: 699090 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1039089 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1220576 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0111. Min Act: -0.0003

Data Index: 61200 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0106. Min Act: -0.0003

Data Index: 769661 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1298362 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0105. Min Act: -0.0003

Data Index: 937329 (C4 (Web Text))

Max Activating Token Index: 783