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

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

Neuron 97 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0002

Data Index: 587203 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0843. Min Act: -0.0003

Data Index: 1289758 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0860. Min Act: -0.0002

Data Index: 220041 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0813. Min Act: -0.0003

Data Index: 754861 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1160529 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0810. Min Act: -0.0003

Data Index: 412857 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0825. Min Act: -0.0004

Data Index: 1109590 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0809. Min Act: -0.0002

Data Index: 449477 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0774. Min Act: -0.0002

Data Index: 29834 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1242848 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0766. Min Act: -0.0003

Data Index: 442171 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0790. Min Act: -0.0002

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0767. Min Act: -0.0003

Data Index: 150357 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0783. Min Act: -0.0003

Data Index: 348586 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0800. Min Act: -0.0002

Data Index: 669290 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1257458 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0782. Min Act: -0.0003

Data Index: 166772 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1046650 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0764. Min Act: -0.0002

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 940