Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1563 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1200046 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1059250 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0117. Min Act: -0.0006

Data Index: 253764 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1301566 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0111. Min Act: -0.0006

Data Index: 848407 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1316462 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1022892 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0101. Min Act: -0.0006

Data Index: 695885 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1354012 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0101. Min Act: -0.0005

Data Index: 475404 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0099. Min Act: -0.0006

Data Index: 885071 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0111. Min Act: -0.0006

Data Index: 757151 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0106. Min Act: -0.0006

Data Index: 398921 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0100. Min Act: -0.0006

Data Index: 551566 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0097. Min Act: -0.0006

Data Index: 800413 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0081. Min Act: -0.0006

Data Index: 624099 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0098. Min Act: -0.0006

Data Index: 678211 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0097. Min Act: -0.0006

Data Index: 179862 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1404937 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1412888 (Python Code)

Max Activating Token Index: 503