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

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

Neuron 780 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: 0.0887. Min Range: -0.0887

Max Act: 0.0887. Min Act: -0.0006

Data Index: 958193 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0783. Min Act: -0.0006

Data Index: 197049 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0752. Min Act: -0.0006

Data Index: 714866 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0717. Min Act: -0.0006

Data Index: 261406 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0712. Min Act: -0.0006

Data Index: 892835 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0686. Min Act: -0.0006

Data Index: 1266889 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0684. Min Act: -0.0006

Data Index: 1310951 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0722. Min Act: -0.0006

Data Index: 138581 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0692. Min Act: -0.0006

Data Index: 1130396 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0691. Min Act: -0.0006

Data Index: 855386 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0665. Min Act: -0.0006

Data Index: 1029981 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0662. Min Act: -0.0006

Data Index: 808332 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0648. Min Act: -0.0006

Data Index: 772000 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0658. Min Act: -0.0006

Data Index: 557485 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0634. Min Act: -0.0006

Data Index: 1261593 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0655. Min Act: -0.0006

Data Index: 629966 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0649. Min Act: -0.0006

Data Index: 644980 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0635. Min Act: -0.0006

Data Index: 899461 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0669. Min Act: -0.0006

Data Index: 598756 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0651. Min Act: -0.0006

Data Index: 995513 (C4 (Web Text))

Max Activating Token Index: 574