Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0005

Data Index: 200241 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0634. Min Act: -0.0005

Data Index: 798122 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0631. Min Act: -0.0005

Data Index: 1323756 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0621. Min Act: -0.0005

Data Index: 1330670 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0599. Min Act: -0.0005

Data Index: 1180259 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0609. Min Act: -0.0005

Data Index: 468303 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0617. Min Act: -0.0005

Data Index: 145932 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0624. Min Act: -0.0005

Data Index: 1063620 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0588. Min Act: -0.0005

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0601. Min Act: -0.0005

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0581. Min Act: -0.0005

Data Index: 1052735 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0576. Min Act: -0.0005

Data Index: 228998 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0565. Min Act: -0.0005

Data Index: 737101 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0556. Min Act: -0.0005

Data Index: 84490 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0581. Min Act: -0.0005

Data Index: 40177 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0588. Min Act: -0.0005

Data Index: 672508 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0588. Min Act: -0.0005

Data Index: 172894 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0617. Min Act: -0.0005

Data Index: 229217 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0587. Min Act: -0.0005

Data Index: 753004 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0568. Min Act: -0.0005

Data Index: 50878 (C4 (Web Text))

Max Activating Token Index: 363