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

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

Neuron 1426 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1588. Min Act: -0.0003

Data Index: 117433 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.2788. Min Act: -0.0003

Data Index: 1125205 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1141. Min Act: -0.0003

Data Index: 1020375 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1250. Min Act: -0.0003

Data Index: 198305 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9767. Min Act: -0.0003

Data Index: 1286088 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0828. Min Act: -0.0003

Data Index: 703078 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1385. Min Act: -0.0003

Data Index: 103078 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9473. Min Act: -0.0003

Data Index: 786727 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9421. Min Act: -0.0003

Data Index: 145871 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9981. Min Act: -0.0003

Data Index: 1197115 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9834. Min Act: -0.0003

Data Index: 776878 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.1212. Min Act: -0.0003

Data Index: 956417 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0991. Min Act: -0.0003

Data Index: 669979 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9695. Min Act: -0.0003

Data Index: 171648 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.2788. Min Range: -1.2788

Max Act: 1.0913. Min Act: -0.0003

Data Index: 157882 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9522. Min Act: -0.0003

Data Index: 1157149 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9685. Min Act: -0.0003

Data Index: 138559 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8930. Min Act: -0.0003

Data Index: 1241350 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9044. Min Act: -0.0003

Data Index: 1197277 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9256. Min Act: -0.0003

Data Index: 188787 (C4 (Web Text))

Max Activating Token Index: 1015