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

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

Neuron 1816 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: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0006

Data Index: 995667 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0006

Data Index: 737430 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1410342 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0006

Data Index: 120554 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1257692 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1628820 (Python Code)

Max Activating Token Index: 527

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0006

Data Index: 794167 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0006

Data Index: 856598 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0006

Data Index: 429774 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1019815 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0006

Data Index: 737967 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0117. Min Act: -0.0006

Data Index: 153909 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0006

Data Index: 621506 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0122. Min Act: -0.0006

Data Index: 911492 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1397633 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0006

Data Index: 337357 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0006

Data Index: 501667 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0006

Data Index: 724107 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0109. Min Act: -0.0006

Data Index: 369355 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1415933 (Python Code)

Max Activating Token Index: 564