Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2550 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.8934. Min Act: -0.0000

Data Index: 753313 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.9217. Min Act: -0.0000

Data Index: 485401 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.9321. Min Act: -0.0000

Data Index: 843484 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1211608 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.8326. Min Act: -0.0000

Data Index: 621383 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.8175. Min Act: -0.0000

Data Index: 701447 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1056838 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.8062. Min Act: -0.0000

Data Index: 487367 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.6951. Min Act: -0.0000

Data Index: 153142 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7146. Min Act: -0.0000

Data Index: 45614 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1018653 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1313891 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7178. Min Act: -0.0000

Data Index: 588886 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1205060 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7052. Min Act: -0.0000

Data Index: 775643 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.7242. Min Act: -0.0000

Data Index: 813569 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1041089 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.6568. Min Act: -0.0000

Data Index: 485874 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1327478 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.9321. Min Range: -0.9321

Max Act: 0.6072. Min Act: -0.0000

Data Index: 16376 (C4 (Web Text))

Max Activating Token Index: 117