Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4649 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7227. Min Act: -0.0000

Data Index: 278970 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1135523 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7055. Min Act: -0.0000

Data Index: 687679 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6844. Min Act: -0.0000

Data Index: 801284 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6835. Min Act: -0.0000

Data Index: 933698 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1088704 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6709. Min Act: -0.0000

Data Index: 981402 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6353. Min Act: -0.0000

Data Index: 131220 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1356396 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1311743 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5803. Min Act: -0.0000

Data Index: 957824 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5808. Min Act: -0.0000

Data Index: 6794 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5866. Min Act: -0.0000

Data Index: 125448 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5507. Min Act: -0.0000

Data Index: 645480 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5659. Min Act: -0.0000

Data Index: 160066 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1265487 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5717. Min Act: -0.0000

Data Index: 533831 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5897. Min Act: -0.0000

Data Index: 907098 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5467. Min Act: -0.0000

Data Index: 698915 (C4 (Web Text))

Max Activating Token Index: 242