Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2522 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1608872 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0003

Data Index: 480676 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0137. Min Act: -0.0003

Data Index: 571194 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1653763 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0135. Min Act: -0.0004

Data Index: 931596 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1467041 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0129. Min Act: -0.0003

Data Index: 135260 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1354535 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1360484 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0121. Min Act: -0.0003

Data Index: 675238 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0003

Data Index: 425868 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1347018 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0120. Min Act: -0.0003

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0003

Data Index: 427549 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0003

Data Index: 319368 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1362721 (Python Code)

Max Activating Token Index: 645

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0116. Min Act: -0.0003

Data Index: 26691 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1616564 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1447035 (Python Code)

Max Activating Token Index: 648