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

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

Neuron 1370 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: 0.4900. Min Range: -0.4900

Max Act: 0.4900. Min Act: -0.0002

Data Index: 999952 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3815. Min Act: -0.0002

Data Index: 1181980 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3802. Min Act: -0.0002

Data Index: 193538 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3086. Min Act: -0.0002

Data Index: 1115 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3101. Min Act: -0.0002

Data Index: 722665 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3093. Min Act: -0.0002

Data Index: 259130 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3024. Min Act: -0.0002

Data Index: 819180 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2557. Min Act: -0.0002

Data Index: 377556 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2975. Min Act: -0.0002

Data Index: 440229 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2929. Min Act: -0.0002

Data Index: 169412 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2755. Min Act: -0.0002

Data Index: 801362 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2929. Min Act: -0.0002

Data Index: 723328 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2783. Min Act: -0.0002

Data Index: 867626 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2652. Min Act: -0.0002

Data Index: 324647 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2810. Min Act: -0.0002

Data Index: 1020974 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2799. Min Act: -0.0002

Data Index: 1254311 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2843. Min Act: -0.0002

Data Index: 988449 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2539. Min Act: -0.0002

Data Index: 340342 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2367. Min Act: -0.0002

Data Index: 728576 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2685. Min Act: -0.0002

Data Index: 372855 (C4 (Web Text))

Max Activating Token Index: 646