Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1796 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0861. Min Act: -0.0003

Data Index: 339358 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0836. Min Act: -0.0003

Data Index: 403193 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0802. Min Act: -0.0003

Data Index: 555992 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0850. Min Act: -0.0003

Data Index: 544436 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0814. Min Act: -0.0003

Data Index: 441345 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0781. Min Act: -0.0003

Data Index: 312190 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0845. Min Act: -0.0003

Data Index: 1293001 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0839. Min Act: -0.0004

Data Index: 368603 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1246144 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0870. Min Act: -0.0003

Data Index: 116513 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1299794 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1358057 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0801. Min Act: -0.0004

Data Index: 1016087 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0797. Min Act: -0.0003

Data Index: 329572 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0762. Min Act: -0.0003

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0791. Min Act: -0.0003

Data Index: 567208 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0760. Min Act: -0.0003

Data Index: 389850 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0785. Min Act: -0.0003

Data Index: 12108 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0787. Min Act: -0.0003

Data Index: 119832 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0790. Min Act: -0.0003

Data Index: 975698 (C4 (Web Text))

Max Activating Token Index: 450