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

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

Neuron 1938 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.7754. Min Act: -0.0001

Data Index: 1061340 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.7096. Min Act: -0.0001

Data Index: 531000 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.6654. Min Act: -0.0001

Data Index: 1487046 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.7491. Min Act: -0.0001

Data Index: 346325 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5138. Min Act: -0.0001

Data Index: 93622 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.6101. Min Act: -0.0001

Data Index: 725368 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.6237. Min Act: -0.0001

Data Index: 99018 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5429. Min Act: -0.0001

Data Index: 397069 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5469. Min Act: -0.0001

Data Index: 717899 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4362. Min Act: -0.0001

Data Index: 1177163 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5100. Min Act: -0.0001

Data Index: 819688 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4265. Min Act: -0.0001

Data Index: 380261 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4210. Min Act: -0.0001

Data Index: 1524712 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4104. Min Act: -0.0001

Data Index: 400658 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4377. Min Act: -0.0001

Data Index: 1621272 (Python Code)

Max Activating Token Index: 840

Text #15

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3112. Min Act: -0.0001

Data Index: 1054083 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4127. Min Act: -0.0001

Data Index: 1098351 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3983. Min Act: -0.0001

Data Index: 1507373 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2915. Min Act: -0.0001

Data Index: 732679 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2421. Min Act: -0.0001

Data Index: 25164 (C4 (Web Text))

Max Activating Token Index: 82