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

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

Neuron 715 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: 0.0915. Min Range: -0.0915

Max Act: 0.0914. Min Act: -0.0003

Data Index: 296732 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0003

Data Index: 198200 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0897. Min Act: -0.0003

Data Index: 300494 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1239461 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0854. Min Act: -0.0003

Data Index: 819188 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0855. Min Act: -0.0003

Data Index: 137300 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0862. Min Act: -0.0003

Data Index: 581793 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0855. Min Act: -0.0003

Data Index: 571513 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0830. Min Act: -0.0003

Data Index: 47277 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1280935 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0833. Min Act: -0.0003

Data Index: 57288 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0834. Min Act: -0.0003

Data Index: 707426 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0809. Min Act: -0.0003

Data Index: 1163760 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0794. Min Act: -0.0003

Data Index: 118504 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0803. Min Act: -0.0003

Data Index: 686861 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0761. Min Act: -0.0003

Data Index: 974679 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0807. Min Act: -0.0003

Data Index: 694176 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0778. Min Act: -0.0003

Data Index: 655985 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0767. Min Act: -0.0003

Data Index: 495736 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0779. Min Act: -0.0003

Data Index: 321616 (C4 (Web Text))

Max Activating Token Index: 29