Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2724 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0002

Data Index: 379250 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0772. Min Act: -0.0002

Data Index: 520713 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0777. Min Act: -0.0002

Data Index: 562127 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0859. Min Act: -0.0002

Data Index: 536471 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1301238 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0770. Min Act: -0.0002

Data Index: 421049 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1283873 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0731. Min Act: -0.0002

Data Index: 590496 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1009300 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0671. Min Act: -0.0002

Data Index: 201602 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0800. Min Act: -0.0002

Data Index: 550707 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0693. Min Act: -0.0002

Data Index: 948309 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1311824 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1105572 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0656. Min Act: -0.0002

Data Index: 649833 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0731. Min Act: -0.0002

Data Index: 420024 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1080631 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0752. Min Act: -0.0002

Data Index: 237420 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0681. Min Act: -0.0002

Data Index: 801778 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0653. Min Act: -0.0002

Data Index: 485630 (C4 (Web Text))

Max Activating Token Index: 191