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

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

Neuron 527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.8686. Min Act: -0.0000

Data Index: 690704 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.6449. Min Act: -0.0000

Data Index: 825710 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1186039 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4194. Min Act: -0.0000

Data Index: 355385 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4290. Min Act: -0.0000

Data Index: 380749 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4111. Min Act: -0.0000

Data Index: 468277 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3191. Min Act: -0.0000

Data Index: 308746 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3866. Min Act: -0.0000

Data Index: 598418 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1273913 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1215916 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4619. Min Act: -0.0000

Data Index: 542712 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3620. Min Act: -0.0000

Data Index: 901109 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3530. Min Act: -0.0000

Data Index: 990412 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3207. Min Act: -0.0000

Data Index: 584474 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4016. Min Act: -0.0000

Data Index: 957449 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3115. Min Act: -0.0000

Data Index: 790565 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3057. Min Act: -0.0000

Data Index: 917243 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2756. Min Act: -0.0000

Data Index: 892721 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2731. Min Act: -0.0000

Data Index: 696288 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2707. Min Act: -0.0000

Data Index: 220806 (C4 (Web Text))

Max Activating Token Index: 889