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

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

Neuron 1559 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0002

Data Index: 129278 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1095719 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1090411 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0798. Min Act: -0.0002

Data Index: 625714 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0794. Min Act: -0.0002

Data Index: 786012 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0771. Min Act: -0.0002

Data Index: 79451 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0764. Min Act: -0.0002

Data Index: 467115 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1223169 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1102006 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0704. Min Act: -0.0002

Data Index: 291904 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0727. Min Act: -0.0002

Data Index: 123623 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1351537 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0712. Min Act: -0.0002

Data Index: 645532 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0731. Min Act: -0.0002

Data Index: 719189 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0688. Min Act: -0.0001

Data Index: 654466 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1086205 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0710. Min Act: -0.0002

Data Index: 428352 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0705. Min Act: -0.0002

Data Index: 315290 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1251589 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0705. Min Act: -0.0001

Data Index: 808011 (C4 (Web Text))

Max Activating Token Index: 304